com.mcparmory/elevenlabs
OCI · GHCR.IO/MCPARMORY/ELEVENLABS:1.0.3 · 2 COMPONENTS · SCANNED SEP 20
Convert text to speech, transcribe audio, and dub videos with AI voices
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- Malware scan not yet available for this package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 131 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability70
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 38535 tokens (~149/item across 258 items; 258 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety95
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 32 of 40 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "isolate_audio" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Partial
- An AI judge read all 258 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
How do I install the com.mcparmory/elevenlabs MCP server?
com.mcparmory/elevenlabs runs locally as a container image, launched with docker run --rm -i ghcr.io/mcparmory/elevenlabs:1.0.3. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/mcparmory/elevenlabs:1.0.3
claude mcp add com-mcparmory-elevenlabs -- docker run --rm -i ghcr.io/mcparmory/elevenlabs:1.0.3
{
"mcpServers": {
"com-mcparmory-elevenlabs": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/elevenlabs:1.0.3"
]
}
}
} {
"servers": {
"com-mcparmory-elevenlabs": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/elevenlabs:1.0.3"
]
}
}
} codex mcp add com-mcparmory-elevenlabs -- docker run --rm -i ghcr.io/mcparmory/elevenlabs:1.0.3
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-mcparmory-elevenlabs": {
"type": "local",
"command": [
"docker",
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/elevenlabs:1.0.3"
],
"enabled": true
}
}
} mcp_servers:
com-mcparmory-elevenlabs:
command: "docker"
args: ["run", "--rm", "-i", "ghcr.io/mcparmory/elevenlabs:1.0.3"] {
"McpServers": {
"com-mcparmory-elevenlabs": {
"Transport": "stdio",
"Command": "docker",
"Arguments": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/elevenlabs:1.0.3"
]
}
}
} {
"mcpServers": {
"com-mcparmory-elevenlabs": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/elevenlabs:1.0.3"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 −3
- Stability: pass → 0.80 functional
- 18 Sept 26 +1
- Stability: 0.97 → pass security
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −3
- Stability: pass → 0.80 functional
- 11 Sept 26 +1
- Stability: 0.97 → pass security
- 9 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 7 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed oci/ghcr.io/mcparmory/elevenlabs:1.0.3
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
add_dubbing_language Add Dubbing Language ~91
Add a supported language to a dubbing project resource. The language is registered but does not automatically generate transcripts, translations, or audio content.
| Name | Type | Req | Description |
|---|---|---|---|
| dubbing_id | string | yes | The unique identifier of the dubbing project to which the language will be added. |
| language | string | – | The target language code in ElevenLabs Turbo V2/V2.5 format to add to the dubbing resource. |
No output schema declared.
No examples provided.
add_group_member Add Group Member ~64
Adds a workspace member to a user group. Requires group_members_manage permission.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | The email address of the workspace member to add to the group. | |
| group_id | string | yes | The unique identifier of the group to which the member will be added. |
No output schema declared.
No examples provided.
add_pronunciation_rules Add Pronunciation Rules ~104
Add or update pronunciation rules in a dictionary. Rules with duplicate string_to_replace values will replace existing rules.
| Name | Type | Req | Description |
|---|---|---|---|
| pronunciation_dictionary_id | string | yes | The unique identifier of the pronunciation dictionary to modify. |
| rules | array | yes | An ordered list of pronunciation rules to add or update. Each rule must be either an alias rule (mapping one string to another alias) or a phoneme rule (mapping a string to a phoneme in a specified a… |
No output schema declared.
No examples provided.
add_shared_voice Add Shared Voice ~126
Add a shared voice from another user to your personal voice collection. The voice will be displayed in your voice dropdown with a custom name you assign.
| Name | Type | Req | Description |
|---|---|---|---|
| bookmarked | boolean | – | Whether to bookmark this voice for quick access in your collection. |
| new_name | string | yes | The display name for this voice in your voice collection. This name will appear in your voice selection dropdown. |
| public_user_id | string | yes | The public user ID of the ElevenLabs user who owns the shared voice. |
| voice_id | string | yes | The unique identifier of the voice to add to your collection. |
No output schema declared.
No examples provided.
add_speaker Add Speaker ~162
Add a new speaker to a dubbing project with a specified voice and optional styling. Each speaker represents a distinct voice track within the dubbing resource.
| Name | Type | Req | Description |
|---|---|---|---|
| dubbing_id | string | yes | The unique identifier of the dubbing project to which the speaker will be added. |
| speaker_name | string | – | A human-readable label for this speaker to identify it within the dubbing project. |
| voice_id | string | – | The voice identifier to use for this speaker. Can be a voice from the ElevenLabs voice library or a special clone type for custom voice cloning. |
| voice_style | number | – | The voice style intensity for models that support style control. Valid range is 0.0 to 1.0, with 1.0 as the default. |
No output schema declared.
No examples provided.
add_text_document Add Text Document ~82
Add a text document to the knowledge base. The document will be indexed and made available for retrieval and analysis.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | A human-readable name for the document. If not provided, a default name will be generated. |
| text | string | yes | The text content to be added to the knowledge base. This will be indexed for search and retrieval. |
No output schema declared.
No examples provided.
add_voice_samples Add Voice Samples ~143
Add audio samples to a PVC (Personal Voice Clone) to enhance voice quality and training data. Optionally remove background noise from samples to improve voice clarity.
| Name | Type | Req | Description |
|---|---|---|---|
| files | array | yes | Base64-encoded file content for upload. Audio files to add to the voice. Provide one or more audio files in supported formats to expand the voice training dataset. |
| remove_background_noise | boolean | – | Enable automatic background noise removal from audio samples using audio isolation. Disable if samples contain minimal background noise, as processing may reduce quality. |
| voice_id | string | yes | The unique identifier of the PVC voice to add samples to. Use the voices list endpoint to retrieve available voice IDs. |
No output schema declared.
No examples provided.
align_audio_to_text Align Audio to Text ~151
Synchronize an audio file with a text transcript to extract precise timing information for each character and word. Supports all major audio formats up to 1GB in size.
| Name | Type | Req | Description |
|---|---|---|---|
| enabled_spooled_file | boolean | – | Enable streaming processing for large files that cannot fit in memory. When true, the file is streamed to the server and processed in chunks. |
| file | string | yes | Base64-encoded file content for upload. The audio file to align with the transcript. Supports all major audio formats with a maximum file size of 1GB. |
| text | string | yes | The text transcript to align with the audio. Can be in any text format; diarization (speaker identification) is not currently supported. |
No output schema declared.
No examples provided.
apply_pronunciation_dictionaries Apply Pronunciation Dictionaries ~129
Apply pronunciation dictionaries to a Studio project. The operation automatically marks affected text for reconversion when dictionaries are added or removed.
| Name | Type | Req | Description |
|---|---|---|---|
| invalidate_affected_text | boolean | – | Whether to automatically mark text in the project for reconversion when dictionaries are applied or removed. |
| project_id | string | yes | The unique identifier of the Studio project to which pronunciation dictionaries will be applied. |
| pronunciation_dictionary_locators | array | yes | An ordered list of pronunciation dictionary references to apply to the project. Each reference must include the dictionary ID and its version ID. Multiple dictionaries can be specified as separate fo… |
No output schema declared.
No examples provided.
approve_mcp_server_tool Approve MCP Server Tool ~166
Grant approval for a specific MCP tool when the server is configured to use per-tool approval mode. This enables fine-grained control over which tools are available for use.
| Name | Type | Req | Description |
|---|---|---|---|
| approval_policy | string | – | The approval policy that determines whether this tool requires explicit approval before each use or is automatically approved. |
| input_schema | object | – | The input schema that defines the parameters and structure expected by the MCP tool, as defined on the MCP server before any ElevenLabs processing. |
| mcp_server_id | string | yes | The unique identifier of the MCP Server to which the tool approval applies. |
| tool_description | string | yes | A human-readable description of what the MCP tool does and its purpose. |
| tool_name | string | yes | The name of the MCP tool being approved for use. |
No output schema declared.
No examples provided.
batch_compute_rag_indexes Batch Compute RAG Indexes ~82
Computes and retrieves RAG (Retrieval-Augmented Generation) indexes for multiple knowledge base documents in a single batch operation. Supports up to 100 documents per request for efficient index creation and retrieval.
| Name | Type | Req | Description |
|---|---|---|---|
| items | array | yes | Array of RAG index requests for knowledge base documents. Each item specifies a document to index. Order is preserved in the response. |
No output schema declared.
No examples provided.
calculate_llm_expected_cost Calculate LLM Expected Cost ~146
Calculate the expected cost of using various LLM models based on prompt length, knowledge base size, and RAG configuration. Returns a list of available models with their associated usage costs.
| Name | Type | Req | Description |
|---|---|---|---|
| number_of_pages | integer | yes | The total number of pages in PDF documents or URLs indexed in the agent's knowledge base. Used to estimate retrieval and processing costs when RAG is enabled. |
| prompt_length | integer | yes | The length of the input prompt in characters. This determines the token consumption for the initial request. |
| rag_enabled | boolean | yes | Whether Retrieval-Augmented Generation (RAG) is enabled. When enabled, the cost calculation includes knowledge base retrieval and context augmentation overhead. |
No output schema declared.
No examples provided.
cancel_batch_call Cancel Batch Call ~49
Cancel a running batch call and set all recipients to cancelled status. This operation terminates the batch calling process immediately.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | The unique identifier of the batch call to cancel. |
No output schema declared.
No examples provided.
compose_music Compose Music ~375
Generate and stream composed music from either a text prompt or a detailed composition plan. Supports various audio formats and customizable musical styles.
| Name | Type | Req | Description |
|---|---|---|---|
| composition_planNegative_global_styles | array | yes | Musical styles and directions to exclude from the entire composition. Use English language for best results. |
| composition_planPositive_global_styles | array | yes | Musical styles and directions to include throughout the entire composition. Use English language for best results. |
| composition_planSections | array | yes | Ordered array defining distinct sections of the song, each with its own musical characteristics and transitions. |
| force_instrumental | boolean | – | When enabled, ensures the generated composition contains no vocals. Only applicable with prompt-based generation. |
| model_id | string | – | The generative model version to use for music composition. |
| music_length_ms | integer | – | Target duration for the generated composition in milliseconds. Only applicable when using prompt-based generation. If omitted, the model determines length based on the prompt. |
| music_promptNegative_global_styles | array | yes | Musical styles and directions to exclude from the entire composition. Use English language for best results. |
| music_promptPositive_global_styles | array | yes | Musical styles and directions to include throughout the entire composition. Use English language for best results. |
| music_promptSections | array | yes | Ordered array defining distinct sections of the song, each with its own musical characteristics and transitions. |
| output_format | string | – | Audio output format specified as codec, sample rate, and bitrate. Higher bitrates and sample rates may require elevated subscription tiers. |
| prompt | string | – | Simple text description to generate a song from. Mutually exclusive with composition_plan. Use English for optimal results. |
| use_phonetic_names | boolean | – | When enabled, proper names in the prompt are phonetically spelled for improved lyrical pronunciation while preserving original names in word-level timestamps. |
No output schema declared.
No examples provided.
compose_song Compose Song ~443
Generate a complete song from either a text prompt or a detailed composition plan, with control over musical style, structure, and audio output format.
| Name | Type | Req | Description |
|---|---|---|---|
| composition_planNegative_global_styles | array | yes | Array of musical styles and directions to exclude from the entire song. Specify in English for optimal results. |
| composition_planPositive_global_styles | array | yes | Array of musical styles and directions to include throughout the entire song. Specify in English for optimal results. |
| composition_planSections | array | yes | Ordered array defining the song structure, including individual sections with their characteristics and durations. |
| force_instrumental | boolean | – | When enabled, ensures the generated song contains no vocals and is purely instrumental. Only applicable with prompt-based generation. |
| model_id | string | – | AI model version to use for music generation. |
| music_length_ms | integer | – | Target song duration in milliseconds. Only used with prompt-based generation. The model will adjust to fit this duration if provided. |
| music_promptNegative_global_styles | array | yes | Array of musical styles and directions to exclude from the entire song. Specify in English for optimal results. |
| music_promptPositive_global_styles | array | yes | Array of musical styles and directions to include throughout the entire song. Specify in English for optimal results. |
| music_promptSections | array | yes | Ordered array defining the song structure, including individual sections with their characteristics and durations. |
| output_format | string | – | Audio output format specified as codec_sample_rate_bitrate (e.g., mp3 at 44.1kHz with 128kbps bitrate). Higher bitrates and PCM formats require appropriate subscription tier. |
| prompt | string | – | Simple text description of the song to generate. Cannot be combined with composition_plan. Use this for quick, straightforward song generation. |
| respect_sections_durations | boolean | – | Controls section duration enforcement in composition plans. When true, strictly respects each section's specified duration. When false, allows duration adjustments for improved quality and latency wh… |
| use_phonetic_names | boolean | – | When enabled, proper names in the prompt are phonetically spelled for improved lyrical pronunciation while preserving original names in word-level timestamps. |
No output schema declared.
No examples provided.
compose_song_detailed Compose Song Detailed ~471
Generate a complete song with detailed metadata from either a text prompt or a structured composition plan. Returns audio file and optional word-level timestamps.
| Name | Type | Req | Description |
|---|---|---|---|
| composition_planNegative_global_styles | array | yes | Musical styles and directions to exclude from the entire song when using composition_plan. Use English language for optimal results. |
| composition_planPositive_global_styles | array | yes | Musical styles and directions to include throughout the entire song when using composition_plan. Use English language for optimal results. |
| composition_planSections | array | yes | Ordered array of song sections for composition_plan, each with duration, style, and lyrical content specifications. Order determines playback sequence. |
| force_instrumental | boolean | – | When enabled, ensures the generated song contains no vocals. Only works with prompt-based generation. |
| model_id | string | – | AI model version to use for music generation. |
| music_length_ms | integer | – | Target song duration in milliseconds. Only applicable with prompt-based generation. If omitted, the model automatically determines length based on prompt content. |
| music_promptNegative_global_styles | array | yes | Musical styles and directions to exclude from the entire song. Use English language for optimal results. |
| music_promptPositive_global_styles | array | yes | Musical styles and directions to include throughout the entire song. Use English language for optimal results. |
| music_promptSections | array | yes | Ordered array of song sections, each with duration, style, and lyrical content specifications. Order determines playback sequence. |
| output_format | string | – | Audio output format specified as codec, sample rate, and bitrate. Higher bitrates and sample rates may require elevated subscription tiers. |
| prompt | string | – | Text-based prompt describing the song to generate. Mutually exclusive with composition_plan. Provide creative direction, mood, genre, and lyrical themes. |
| respect_sections_durations | boolean | – | Controls section duration enforcement in composition_plan. When true, strictly respects each section's specified duration. When false, allows duration flexibility for improved quality and latency whi… |
| use_phonetic_names | boolean | – | When enabled, proper names in the prompt are phonetically spelled for improved lyrical pronunciation while preserving original names in word timestamps. |
| with_timestamps | boolean | – | When enabled, the response includes precise word-level timestamps indicating when each lyric occurs in the generated audio. |
No output schema declared.
No examples provided.
configure_mcp_server Configure MCP Server ~316
Update configuration settings for an MCP server, including approval policies, audio behavior, execution modes, and authentication. Changes apply to all tools provided by this server.
| Name | Type | Req | Description |
|---|---|---|---|
| approval_policy | string | – | The approval workflow mode for tool execution from this server. Controls whether tools require manual approval before execution. |
| auth_connection | – | – | Optional authentication connection configuration for establishing secure communication with this MCP server. |
| disable_compression | boolean | – | When enabled, disables HTTP compression for requests to this MCP server to reduce processing overhead. |
| disable_interruptions | boolean | – | When enabled, prevents user interruptions during tool execution, overriding the server's default setting. |
| execution_mode | string | – | Determines the execution timing for tools from this server. Immediate executes right away, post_tool_speech waits for narration, and async runs in the background. |
| force_pre_tool_speech | boolean | – | When enabled, forces the system to speak tool descriptions aloud before execution, overriding the server's default setting. |
| mcp_server_id | string | yes | The unique identifier of the MCP server to configure. |
| request_headers | object | – | HTTP headers to include in all requests sent to this MCP server, such as custom authentication or tracking headers. |
| secret_id | string | yes | The secret identifier for credentials or API keys used to authenticate with this MCP server. |
| tool_call_sound | string | – | The sound effect to play during tool execution for all tools from this server. |
| tool_call_sound_behavior | string | – | Controls when the tool call sound plays during execution. |
No output schema declared.
No examples provided.
configure_voice_settings Configure Voice Settings ~236
Configure voice parameters for a specific voice, including stability, similarity, style, and speed adjustments. These settings control how the voice is generated and how closely it adheres to the original voice characteristics.
| Name | Type | Req | Description |
|---|---|---|---|
| similarity_boost | number | – | Controls how closely the generated voice matches the original voice characteristics. Higher values enforce stricter adherence to the original voice, while lower values allow more deviation. |
| speed | number | – | Adjusts speech playback speed relative to normal rate. Use 1.0 for default speed, values below 1.0 to slow down, and values above 1.0 to speed up. |
| stability | number | – | Controls voice consistency and emotional range. Lower values (closer to 0) produce more varied emotional expression, while higher values (closer to 1) result in more consistent but potentially monoto… |
| style | number | – | Amplifies the stylistic characteristics of the original speaker. Non-zero values increase computational resource usage and may increase latency. |
| voice_id | string | yes | The unique identifier of the voice to configure. Use the list voices endpoint to discover available voice IDs. |
No output schema declared.
No examples provided.
convert_chapter Convert Chapter ~73
Initiates the conversion process for a specific chapter within a Studio project. This asynchronous operation transforms the chapter content into the desired output format.
| Name | Type | Req | Description |
|---|---|---|---|
| chapter_id | string | yes | The unique identifier of the chapter to be converted. |
| project_id | string | yes | The unique identifier of the Studio project containing the chapter to convert. |
No output schema declared.
No examples provided.
convert_speech_to_speech_stream Convert Speech to Speech Stream ~323
Convert audio from one voice to another with streaming output, maintaining full control over emotion, timing, and delivery. The input audio's content and emotional characteristics drive the generated speech in the target voice.
| Name | Type | Req | Description |
|---|---|---|---|
| audio | string | yes | Base64-encoded file content for upload. The source audio file containing the content and emotional characteristics that will control the generated speech output. |
| model_id | string | – | The model identifier to use for voice conversion. Verify the model supports speech-to-speech conversion via the can_do_voice_conversion property. |
| output_format | string | – | Audio encoding format for the response, specified as codec_sample_rate_bitrate. Higher bitrates and sample rates may require elevated subscription tiers. |
| remove_background_noise | boolean | – | Enable background noise removal from the input audio using audio isolation. Only applicable when using the Voice Changer model. |
| similarity_boost | number | – | Controls how closely the voice matches the original. Higher values increase similarity. Range: 0.0 to 1.0 |
| stability | number | – | Controls the stability of the voice. Higher values produce more consistent output. Range: 0.0 to 1.0 |
| style | number | – | Controls the style exaggeration of the voice. Range: 0.0 to 1.0 |
| use_speaker_boost | boolean | – | Whether to apply speaker boost for enhanced clarity and presence |
| voice_id | string | yes | The target voice identifier to apply to the input audio. Use the voices endpoint to discover available voices. |
No output schema declared.
No examples provided.
convert_studio_project Convert Studio Project ~51
Initiates conversion of a Studio project and all of its associated chapters. This operation processes the entire project structure for conversion.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | The unique identifier of the Studio project to convert. |
No output schema declared.
No examples provided.
convert_voice Convert Voice ~319
Transform audio from one voice to another while preserving the original emotion, timing, and delivery characteristics. The input audio's content and emotional qualities control the output speech generation.
| Name | Type | Req | Description |
|---|---|---|---|
| audio | string | yes | Base64-encoded file content for upload. The source audio file containing the content and emotional expression to transfer to the target voice. |
| model_id | string | – | The speech-to-speech model to use for conversion. Query available models to verify speech conversion support via the can_do_voice_conversion property. |
| output_format | string | – | Audio encoding format specified as codec_sample_rate_bitrate (e.g., mp3_44100_128). Higher bitrates and PCM formats require higher subscription tiers. |
| remove_background_noise | boolean | – | Enable background noise removal from the input audio using audio isolation. Only applicable when using the Voice Changer model. |
| similarity_boost | number | – | Controls how closely the voice matches the original. Higher values increase similarity. Range: 0.0 to 1.0 |
| stability | number | – | Controls the stability of the voice. Higher values produce more consistent output. Range: 0.0 to 1.0 |
| style | number | – | Controls the style exaggeration of the voice. Range: 0.0 to 1.0 |
| use_speaker_boost | boolean | – | Whether to apply speaker boost for enhanced clarity and presence |
| voice_id | string | yes | The target voice to apply to the audio. Use the voices endpoint to discover available voices and their characteristics. |
No output schema declared.
No examples provided.
create_agent_branch Create Agent Branch ~212
Create a new branch from a specified version of an agent's main branch. Branches allow you to develop and test agent configurations independently before merging changes back to the main branch.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the agent to create a branch for. |
| conversation_config | object | – | Optional configuration changes to apply to conversation settings for this branch. |
| description | string | yes | A description of the branch's purpose or contents. Cannot exceed 4096 characters. |
| edges | object | – | Optional edge definitions for the agent's conversation flow in this branch. |
| name | string | yes | The name of the new branch. Must be unique within the agent and cannot exceed 140 characters. |
| nodes | object | – | Optional node definitions for the agent's conversation flow in this branch. |
| parent_version_id | string | yes | The version ID of the main branch to use as the base for this new branch. |
| platform_settings | object | – | Optional platform-specific settings changes to apply to this branch. |
No output schema declared.
No examples provided.
create_agent_draft Create Agent Draft ~246
Create a new draft version of an agent with specified configuration, platform settings, and workflow structure. Drafts allow you to develop and test agent changes before publishing.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the agent for which to create a draft. |
| branch_id | string | yes | The unique identifier of the agent branch where the draft will be created. |
| conversation_config | object | yes | Configuration object defining conversation behavior, including parameters for dialogue flow, response handling, and interaction settings. |
| edges | object | – | Workflow connections defining how nodes interact. Each edge represents a transition or data flow between nodes in the agent's workflow graph. |
| name | string | yes | A human-readable name for the draft to help identify and organize different versions. |
| nodes | object | – | Workflow nodes representing individual components or steps in the agent's logic. Nodes define actions, decision points, or processing stages. |
| platform_settings | object | yes | Configuration object specifying platform-specific settings such as deployment targets, feature flags, and integration parameters. |
| tags | array | – | Optional labels for categorizing and filtering the agent draft. Tags enable organization by use case, domain, or other classification criteria. |
No output schema declared.
No examples provided.
create_agent_route Create Agent Route ~97
Create Agent
| Name | Type | Req | Description |
|---|---|---|---|
| conversation_config | – | – | Conversation configuration including ASR, TTS, turn handling, and agent prompt settings |
| name | string | – | A name to make the agent easier to find |
| platform_settings | – | – | Platform settings including widget config, auth, privacy, guardrails, and evaluation |
| tags | array | – | Tags to help classify and filter the agent |
| workflow | – | – | Workflow definition with nodes and edges |
No output schema declared.
No examples provided.
create_agent_test Create Agent Test ~372
Creates a new test case for evaluating agent responses. Tests can validate response quality, tool usage, or simulate multi-turn conversations with configurable success criteria.
| Name | Type | Req | Description |
|---|---|---|---|
| chat_history | array | – | Conversation history to provide context for the agent's response. Ordered list of messages representing the dialogue leading up to the test. |
| check_any_tool_matches | boolean | – | When true, the test passes if any tool call matches the criteria. When false, the test fails if the agent returns multiple tool calls. |
| dynamic_variables | object | – | Key-value pairs to substitute into the agent configuration during test execution, enabling parameterized testing. |
| failure_examples | array | – | Reference responses demonstrating failed agent behavior. Used to ensure the agent avoids producing similar problematic responses. |
| from_conversation_metadata | – | – | Metadata from the source conversation if this test was derived from an existing conversation. |
| name | string | yes | Human-readable name for this test case. |
| simulation_environment | string | – | Execution environment for the simulation test. Defaults to production if not specified. |
| simulation_max_turns | integer | – | Maximum number of conversation turns to execute in simulation tests. Controls test duration and complexity. |
| simulation_scenario | string | – | Description of the simulated user scenario and persona for simulation-based tests. Provides context for multi-turn conversation evaluation. |
| success_condition | string | – | Evaluation prompt that determines test success. Should be a boolean-returning prompt that assesses whether the agent's response meets expectations. |
| success_examples | array | – | Reference responses demonstrating successful agent behavior. Used to validate that the agent produces similar quality responses. |
| tool_call_parameters | – | – | Criteria for evaluating tool calls made by the agent. Leave empty to skip tool call validation. |
| type | string | – | Type of test to execute. Determines whether the test evaluates LLM responses or simulated conversations. |
No output schema declared.
No examples provided.
create_audio_project Create Audio Project ~400
Creates an Audio Native enabled project with optional automatic conversion to audio. Returns a project ID and embeddable HTML snippet for audio playback.
| Name | Type | Req | Description |
|---|---|---|---|
| apply_text_normalization | string | – | Controls text normalization behavior. 'auto' lets the system decide, 'on' always applies normalization, 'apply_english' applies normalization assuming English text, and 'off' disables normalization. |
| author | string | – | The author name displayed in the audio player and at the start of the article. Uses the default author from Player settings if not specified. |
| auto_convert | boolean | – | Whether to automatically convert the project content to audio upon creation. |
| file | string | – | Base64-encoded file content for upload. Either txt or HTML input file containing the article content. HTML should be formatted as follows '<html><body><div><p>Your content<… |
| model_id | string | – | The TTS model ID used by the player. Uses the default model from Player settings if not specified. |
| name | string | yes | The name of the audio project. |
| player_colors | string | – | Player colors as a comma-separated pair of hex color codes in format 'text_color,background_color' (e.g., '#FFFFFF,#000000'). If not provided, default colors set in Player settings are used. |
| pronunciation_dictionary_locators | array | – | A list of pronunciation dictionary locators, each containing a pronunciation_dictionary_id and version_id pair. Multiple dictionaries can be applied to customize pronunciation of specific terms. |
| voice_id | string | – | The voice ID used for text-to-speech synthesis. Uses the default voice from Player settings if not specified. |
No output schema declared.
No examples provided.
create_chapter Create Chapter ~72
Creates a new chapter in a Studio project, either as a blank chapter or populated from a URL source.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | The display name for the chapter used for identification and organization within the project. |
| project_id | string | yes | The unique identifier of the Studio project where the chapter will be created. |
No output schema declared.
No examples provided.
create_environment_variable Create Environment Variable ~121
Create a new environment variable for the workspace with environment-specific values. Environment variables enable dynamic configuration management across different deployment environments.
| Name | Type | Req | Description |
|---|---|---|---|
| label | string | yes | A unique identifier label for this environment variable within the workspace. Used to reference the variable in configurations and deployments. |
| type | string | yes | The type or category of the environment variable, determining how it will be processed and used within the workspace. |
| values | object | yes | A mapping of environment names to their corresponding values. Must include at least a 'production' key with its associated value for production deployments. |
No output schema declared.
No examples provided.
create_evaluation Create Evaluation ~138
Trigger a new evaluation for a speech-to-text transcript by specifying the transcript, evaluating agent, and evaluation criteria. Optionally provide custom labels and agent name for context.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the agent performing the evaluation. |
| agent_name | string | – | The display name of the agent performing the evaluation for reference purposes. |
| eval_criterion_id | string | yes | The unique identifier of the evaluation criterion to apply during the evaluation. |
| labels | object | – | Custom labels or metadata to attach to the evaluation as key-value pairs. |
| transcript_id | string | yes | The unique identifier of the transcript to be evaluated. |
No output schema declared.
No examples provided.
create_folder Create Folder ~50
Create a new folder in the knowledge base for organizing and grouping related documents together.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | A human-readable name for the folder. Used to identify and organize document groups within the knowledge base. |
No output schema declared.
No examples provided.
create_knowledge_base_document_from_url Create Knowledge Base Document from URL ~105
Create a knowledge base document by scraping and indexing content from a specified webpage. The agent will use this document to access and reference the webpage content when interacting with users.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | A human-readable label for this document within the knowledge base. Helps identify and organize the document for agent reference. |
| url | string | yes | The complete URL of the webpage to scrape and add to the knowledge base. Must be a valid, publicly accessible web address. |
No output schema declared.
No examples provided.
create_pronunciation_dictionary Create Pronunciation Dictionary ~144
Creates a new pronunciation dictionary from a lexicon .PLS file. The dictionary can be configured with access permissions for workspace collaboration.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | An optional description of the pronunciation dictionary to provide additional context about its contents or purpose. |
| file | string | – | Base64-encoded file content for upload. A lexicon .pls file which we will use to initialize the project with. |
| name | string | yes | The name of the pronunciation dictionary used for identification and reference within the system. |
| workspace_access | string | – | The workspace access level that determines permissions for other users to interact with this dictionary. If not provided, defaults to no access. |
No output schema declared.
No examples provided.
create_pronunciation_dictionary_from_rules Create Pronunciation Dictionary from Rules ~194
Creates a new pronunciation dictionary from provided rules. The dictionary can be configured with access permissions for workspace collaboration.
| Name | Type | Req | Description |
|---|---|---|---|
| alias_rules | array | – | List of alias rules. Each rule is a dict with 'string_to_replace' (str) and 'alias' (str) keys. |
| description | string | – | An optional description of the pronunciation dictionary to provide additional context about its contents or purpose. |
| name | string | yes | The name of the pronunciation dictionary used for identification and reference purposes. |
| phoneme_rules | array | – | List of phoneme rules. Each rule is a dict with 'string_to_replace' (str), 'phoneme' (str), and 'alphabet' (str) keys. |
| workspace_access | string | – | The access level for workspace users. Determines whether users can administer, edit, comment on, or only view the dictionary. Defaults to no access if not specified. |
No output schema declared.
No examples provided.
create_segment Create Segment ~166
Creates a new segment for a speaker in a dubbing project with specified start and end times across all available languages. The segment is created without automatically generating transcripts, translations, or audio content.
| Name | Type | Req | Description |
|---|---|---|---|
| dubbing_id | string | yes | The unique identifier of the dubbing project containing the speaker. |
| end_time | number | yes | The end time of the segment in seconds (relative to the media timeline). Must be greater than the start time. |
| speaker_id | string | yes | The unique identifier of the speaker within the dubbing project. |
| start_time | number | yes | The start time of the segment in seconds (relative to the media timeline). |
| translations | object | – | Optional translations for the segment content, organized by language code. Specify translations for any languages beyond the default project language. |
No output schema declared.
No examples provided.
create_service_account_api_key Create Service Account API Key ~152
Generate a new API key for a service account with specified permissions and optional usage limits. The created key can be used to authenticate requests to the XI API on behalf of the service account.
| Name | Type | Req | Description |
|---|---|---|---|
| character_limit | integer | – | Optional monthly character limit for this API key. When set, requests that would exceed this limit will be rejected, preventing unexpected usage charges. |
| name | string | yes | A human-readable name for the API key to help identify its purpose or usage context. |
| permissions | – | yes | The set of permissions to grant this API key, controlling which XI API operations it can perform. |
| service_account_user_id | string | yes | The unique identifier of the service account for which to create the API key. |
No output schema declared.
No examples provided.
create_studio_project Create Studio Project ~952
Creates a new Studio project for audio content generation. Projects can be initialized as blank, from a document, or from a URL, with customizable voices, audio quality, and metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| apply_text_normalization | string | – | Controls text normalization behavior: 'auto' decides automatically, 'on' always applies, 'apply_english' applies with English assumption, 'off' disables normalization. |
| author | string | – | The author name to include as metadata in downloaded audio files. |
| auto_assign_voices | boolean | – | Whether to automatically assign voices to phrases during project creation. This is an alpha feature. |
| auto_convert | boolean | – | Whether to automatically convert the project to audio immediately upon creation. |
| callback_url | string | – | A webhook URL that receives conversion status notifications for the project and its chapters. Notifications include success/error status with project and chapter IDs. |
| content_blocks | array | – | List of block objects, each with 'sub_type' (e.g., 'p', 'h1', 'h2') and 'nodes' (list of node objects) |
| content_chapters | array | – | List of chapter objects, each with 'name' (string) and 'blocks' (list of block objects) |
| content_nodes | array | – | List of TTS node objects, each with 'type' ('tts_node'), 'text' (string), and 'voice_id' (string) |
| content_type | string | – | The type of content in this project (e.g., Book, Article, Screenplay). |
| create_publishing_read | boolean | – | Whether to create a corresponding read for direct publishing in draft state alongside the project. |
| default_model_id | string | – | The model ID to use for audio generation in this project. Query GET /v1/models to list available models. |
| default_paragraph_voice_id | string | – | The voice ID to use as the default voice for new paragraphs in this project. |
| default_title_voice_id | string | – | The voice ID to use as the default voice for new titles in this project. |
| description | string | – | A description of the Studio project's content and purpose. |
| fiction | string | – | Whether the content is fiction or non-fiction. |
| from_document | string | – | Base64-encoded file content for upload. An optional .epub, .pdf, .txt or similar file can be provided. If provided, we will initialize the Studio project with its content. If this is set, 'from_url'… |
| genres | array | – | A list of genres associated with this project for categorization and discovery. |
| isbn_number | string | – | The ISBN number of the project to include as metadata in downloaded audio files. |
| language | string | – | The primary language of the project content as a two-letter ISO 639-1 language code. |
| mature_content | boolean | – | Whether this project contains mature content that may not be suitable for all audiences. |
| name | string | yes | The name of the Studio project used for identification and display purposes. |
| original_publication_date | string | – | The original publication date of the content in YYYY-MM-DD or YYYY format. |
| pronunciation_dict_ids | array | – | List of pronunciation_dictionary_id values |
| pronunciation_dict_versions | array | – | List of version_id values corresponding to each pronunciation_dictionary_id (must be same length as pronunciation_dict_ids) |
| quality_preset | string | – | The output quality level for generated audio, ranging from standard (128kbps) to ultra lossless (705.6kbps, fully lossless). |
| similarity_boost | number | – | Controls how closely the voice matches the original. Higher values increase similarity. Range: 0.0 to 1.0 |
| source_type | string | – | The initialization type for the project: blank (empty), book (from document), article, genfm, video, or screenplay. |
| stability | number | – | Controls the stability of the voice. Higher values produce more consistent output. Range: 0.0 to 1.0 |
| style | number | – | Controls the style exaggeration of the voice. Range: 0.0 to 1.0 |
| target_audience | string | – | The intended audience demographic for this project's content. |
| use_speaker_boost | boolean | – | Whether to apply speaker boost for enhanced clarity and presence |
| volume_normalization | boolean | – | Whether to apply postprocessing to normalize audio volume to audiobook standards when downloading the project. |
No output schema declared.
No examples provided.
create_tool Create Tool ~80
Register a new tool in the workspace to make it available for use in conversations. The tool configuration defines its name, description, parameters, and execution behavior.
| Name | Type | Req | Description |
|---|---|---|---|
| tool_config | – | yes | The tool configuration object that defines the tool's metadata, input parameters, and behavior. This should include the tool name, description, parameter schema, and any other required configuration… |
No output schema declared.
No examples provided.
create_tool_config_override Create Tool Config Override ~281
Create configuration overrides for a specific MCP tool, allowing fine-grained control over tool execution behavior, audio feedback, and input handling independent of server-level settings.
| Name | Type | Req | Description |
|---|---|---|---|
| assignments | array | – | Dynamic variable assignments that will be available to this MCP tool during execution. Order is preserved as specified. |
| disable_interruptions | boolean | – | When enabled, prevents user interruptions during this tool's execution, overriding the server's default setting. |
| execution_mode | string | – | Determines when this tool executes relative to speech output: immediately, after tool speech completes, or asynchronously. |
| force_pre_tool_speech | boolean | – | When enabled, forces the system to speak a message before executing this tool, overriding the server's default setting. |
| input_overrides | object | – | JSON path mappings to override specific input parameters for this tool, allowing selective input transformation or substitution. |
| mcp_server_id | string | yes | The unique identifier of the MCP server containing the tool to configure. |
| tool_call_sound | string | – | The sound effect to play when this tool is invoked, overriding the server's default sound setting. |
| tool_call_sound_behavior | string | – | Controls when the tool call sound plays: automatically based on context or always when the tool executes. |
| tool_name | string | yes | The exact name of the MCP tool within the server to apply these configuration overrides to. |
No output schema declared.
No examples provided.
create_voice Create Voice ~162
Create a persistent voice from a previously generated voice preview. This endpoint finalizes a voice design by converting a generated_voice_id (obtained from design or remix operations) into a named voice asset.
| Name | Type | Req | Description |
|---|---|---|---|
| generated_voice_id | string | yes | The ID of the generated voice preview to finalize. Obtain this from the response of POST /v1/text-to-voice/design or POST /v1/text-to-voice/:voice_id/remix operations. |
| labels | object | – | Optional metadata tags to associate with the created voice for organization and filtering purposes. |
| voice_description | string | yes | A detailed description of the voice characteristics and use case. Must be between 20 and 1000 characters. |
| voice_name | string | yes | The name for the new voice being created. |
No output schema declared.
No examples provided.
create_voice_pvc Create PVC Voice ~116
Creates a new PVC voice with metadata. Voice samples can be added later to train the voice model.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | Optional description providing context about the voice characteristics and intended use cases. |
| labels | object | – | Optional metadata labels to categorize and describe the voice. Supports language, accent, gender, and age attributes. |
| language | string | yes | The language code for the voice samples and voice model training. |
| name | string | yes | The display name for this voice, shown in voice selection dropdowns and UI. |
No output schema declared.
No examples provided.
create_voice_sample Create Voice Sample ~187
Create a new voice in VoiceLab by uploading audio samples for voice cloning. The voice will be added to your collection and available for use in voice synthesis.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | Optional metadata describing the voice characteristics, tone, and intended use cases. |
| files | array | yes | Base64-encoded file content for upload. Audio file paths for voice cloning samples. Provide multiple recordings to improve voice quality and consistency. Order does not affect processing. |
| labels | – | – | Categorical metadata for voice classification. Supports language code, accent variant, gender, and age range to help organize and filter voices. |
| name | string | yes | The display name for this voice, shown in selection dropdowns and voice management interfaces. |
| remove_background_noise | boolean | – | Enable background noise removal using audio isolation processing. Only use if your samples contain background noise, as it may degrade quality for clean recordings. |
No output schema declared.
No examples provided.
create_workspace_secret Create Workspace Secret ~123
Create a new secret for the Convai workspace. Secrets are securely stored credentials or sensitive values that can be referenced in workspace configurations.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | A unique identifier for the secret within the workspace. Used to reference the secret in configurations and workflows. |
| type | string | yes | The category or classification of the secret (e.g., API key, password, token, connection string). Determines how the secret is handled and validated. |
| value | string | yes | The sensitive value to be securely stored. This value is encrypted and not returned in subsequent API responses. |
No output schema declared.
No examples provided.
delete_agent Delete Agent ~42
Permanently delete an agent and remove it from the system. This action cannot be undone.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the agent to delete. |
No output schema declared.
No examples provided.
delete_agent_draft Delete Agent Draft ~69
Delete a draft version of an agent. This removes the unpublished changes associated with the specified agent and branch.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the agent whose draft should be deleted. |
| branch_id | string | yes | The identifier of the agent branch containing the draft to delete. |
No output schema declared.
No examples provided.
delete_agent_test Delete Agent Test ~49
Deletes an agent response test by its ID. This removes the test configuration and associated test data from the system.
| Name | Type | Req | Description |
|---|---|---|---|
| test_id | string | yes | The unique identifier of the agent response test to delete. |
No output schema declared.
No examples provided.
delete_auth_connection Delete Auth Connection ~48
Delete an authentication connection from the workspace. This removes the stored credentials and configuration for the specified auth connection.
| Name | Type | Req | Description |
|---|---|---|---|
| auth_connection_id | string | yes | The unique identifier of the authentication connection to delete. |
No output schema declared.
No examples provided.
delete_batch_call Delete Batch Call ~49
Permanently delete a batch call and all associated recipient records. Note that conversation history will be retained even after deletion.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | The unique identifier of the batch call to delete. |
No output schema declared.
No examples provided.
delete_chapter Delete Chapter ~61
Permanently deletes a chapter from a Studio project. This action cannot be undone.
| Name | Type | Req | Description |
|---|---|---|---|
| chapter_id | string | yes | The unique identifier of the chapter to delete. |
| project_id | string | yes | The unique identifier of the Studio project containing the chapter to delete. |
No output schema declared.
No examples provided.
delete_conversation Delete Conversation ~41
Permanently delete a conversation and all associated data. This action cannot be undone.
| Name | Type | Req | Description |
|---|---|---|---|
| conversation_id | string | yes | The unique identifier of the conversation to delete. |
No output schema declared.
No examples provided.
What is the com.mcparmory/elevenlabs MCP server?
com.mcparmory/elevenlabs is an MCP server listed in the public MCP registry as com.mcparmory/elevenlabs. Convert text to speech, transcribe audio, and dub videos with AI voices. This page covers its container image (ghcr.io/mcparmory/elevenlabs:1.0.3).
Is the com.mcparmory/elevenlabs MCP server safe to use?
com.mcparmory/elevenlabs scores 48 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the com.mcparmory/elevenlabs MCP server expose?
com.mcparmory/elevenlabs exposes 258 tools: list_speech_history, get_speech_history_item, delete_history_item, get_speech_history_audio, download_speech_items, and 253 more. Their descriptions and schemas cost roughly 38,535 tokens of context every time the server is loaded.
Is the com.mcparmory/elevenlabs MCP server still maintained?
com.mcparmory/elevenlabs is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.