# TTS MCP Server (pypi · tts-mcp-server)

Text-to-speech, AI voiceover, voice cloning and SRT/VTT subtitles for AI agents.

- Trust score: 75/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- oci · `docker.io/miragea/tts-mcp-server`: 41/100, [markdown](https://verifymcp.io/servers/rty2345rr-tts-mcp-server/docker-io-miragea-tts-mcp-server.md), [page](https://verifymcp.io/servers/rty2345rr-tts-mcp-server/docker-io-miragea-tts-mcp-server)
- pypi · `tts-mcp-server`: 75/100 (this document), [markdown](https://verifymcp.io/servers/rty2345rr-tts-mcp-server/tts-mcp-server.md), [page](https://verifymcp.io/servers/rty2345rr-tts-mcp-server/tts-mcp-server)

## Channel facts

- Registry: `pypi`
- Package: `tts-mcp-server`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 31 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to RTY2345RR/miragea-voice-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 1032 tokens (~147/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**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.

## Install

### How do I install the TTS MCP Server server?

TTS MCP Server runs locally as a PyPI package, launched with uvx tts-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add rty2345rr-tts-mcp-server -- uvx tts-mcp-server
```

### Cursor

```json
{
  "mcpServers": {
    "rty2345rr-tts-mcp-server": {
      "command": "uvx",
      "args": [
        "tts-mcp-server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "rty2345rr-tts-mcp-server": {
      "command": "uvx",
      "args": [
        "tts-mcp-server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add rty2345rr-tts-mcp-server -- uvx tts-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "rty2345rr-tts-mcp-server": {
      "type": "local",
      "command": [
        "uvx",
        "tts-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add rty2345rr-tts-mcp-server --command uvx --arg tts-mcp-server
```

### Hermes

```yaml
mcp_servers:
  rty2345rr-tts-mcp-server:
    command: "uvx"
    args: ["tts-mcp-server"]
```

### Netclaw

```json
{
  "McpServers": {
    "rty2345rr-tts-mcp-server": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "tts-mcp-server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add rty2345rr-tts-mcp-server -t stdio -c uvx -a tts-mcp-server
```

### Other

```json
{
  "mcpServers": {
    "rty2345rr-tts-mcp-server": {
      "command": "uvx",
      "args": [
        "tts-mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 75, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-15 (score 60, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-14 (score 75, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-13 (score 60, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-12 (score 75, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-11 (score 60, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-09 (score 75, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-08 (score 60)

First indexed and scored.

## MCP tools (7)

### `miragea_get_capabilities` (~73 tokens)

Get the live voice-engine capabilities for this API key: voice models (expressive, standard), emotion/style tags per model, voice sources, audio formats, speed range, max characters per request, and subtitle formats and upload limits. Read-only. Call this first.

Input parameters:

- `include_raw` (boolean)

### `miragea_list_voices` (~79 tokens)

List the voices (actors) saved in the user's Miragea account, with actor_id, name and language. Use `search` to find a voice by name across pages. Pass the actor_id to the voiceover tools. Read-only.

Input parameters:

- `limit` (integer)
- `offset` (integer)
- `search`

### `miragea_text_to_speech` (~199 tokens)

Generate a voiceover audio file from text (Miragea voice engine) and save it locally. Choose a voice with `actor_id` (from miragea_list_voices) OR `reference_audio_url` (public URL to clone from; add its exact transcript in `reference_text` for the most faithful clone). Optional: model ('expressive' or 'standard'), tags (emotion/style labels from capabilities), speed 0.25-4, format. Returns the saved file path and task_id.

Input parameters:

- `actor_id`
- `format`
- `idempotency_key`
- `language`
- `model`
- `output_path`
- `reference_audio_url`
- `reference_text`
- `speed`
- `tags`
- `text`
- `text_file`
- `wait` (boolean)
- `wait_timeout_seconds`

### `miragea_transcribe` (~140 tokens)

Create subtitles from a local audio or video file (mp3, wav, m4a, mp4, mov, ...) with Miragea speech recognition. Saves SRT by default; also VTT, TXT or JSON (text, language, timed segments). `max_caption_chars` splits long cues for short-form video (e.g. 32-42).

Input parameters:

- `expected_rate`
- `file_path` (string, required)
- `formats`
- `idempotency_key`
- `max_caption_chars` (integer)
- `output_path`
- `wait` (boolean)
- `wait_timeout_seconds`

### `miragea_script_to_voiceover` (~217 tokens)

One shot for video creators: turn a script into a voiceover audio file PLUS matching captions (SRT and VTT by default) ready for CapCut, Premiere, DaVinci Resolve, YouTube or Shorts/TikTok/Reels. Generates speech with Miragea, then times captions by running Miragea recognition on the new audio. caption_text='script' (default) keeps your exact script wording (brand names spelled right) on the recognized timing. Set captions=false for audio only.

Input parameters:

- `actor_id`
- `caption_formats`
- `caption_text` (string)
- `captions` (boolean)
- `format` (string)
- `language`
- `max_caption_chars` (integer)
- `model`
- `name`
- `output_dir`
- `reference_audio_url`
- `reference_text`
- `script`
- `script_file`
- `speed`
- `tags`
- `wait_timeout_seconds`

### `miragea_get_task` (~90 tokens)

Check a Miragea task by task_id and optionally wait for it and save its output (audio file, or subtitles in srt/vtt/txt/json). Use this to resume after a timeout instead of resubmitting.

Input parameters:

- `caption_formats`
- `output_path`
- `task_id` (string, required)
- `wait` (boolean)
- `wait_timeout_seconds`

### `miragea_list_tasks` (~37 tokens)

List recent Miragea tasks (voiceovers and subtitle jobs) for this account, newest first.

Input parameters:

- `limit` (integer)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/rty2345rr-tts-mcp-server/tts-mcp-server#diagnostics

## Score history

- 2026-11-21: 75
- 2026-11-20: 60
- 2026-11-19: 60
- 2026-11-18: 60
- 2026-11-17: 60
- 2026-11-16: 60
- 2026-11-15: 60
- 2026-11-14: 75
- 2026-11-13: 60
- 2026-11-12: 75
- 2026-11-11: 60
- 2026-11-10: 75
- 2026-11-09: 75
- 2026-11-08: 60

## Common questions

### What is the TTS MCP Server server?

TTS MCP Server is listed in the public MCP registry as io.github.RTY2345RR/tts-mcp-server. Text-to-speech, AI voiceover, voice cloning and SRT/VTT subtitles for AI agents. This page covers its PyPI package (tts-mcp-server).

### Is the TTS MCP Server server safe to use?

TTS MCP Server scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 TTS MCP Server server expose?

TTS MCP Server exposes 7 tools: miragea_get_capabilities, miragea_list_voices, miragea_text_to_speech, miragea_transcribe, miragea_script_to_voiceover, and 2 more. Their descriptions and schemas cost roughly 835 tokens of context every time the server is loaded.

### Is the TTS MCP Server server still maintained?

TTS MCP Server is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the TTS MCP Server server under?

TTS MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the TTS MCP Server server?

VerifyMCP ran 15 checks on TTS MCP Server, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about TTS MCP Server: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/tts-mcp-server/
- Socket report: https://socket.dev/pypi/package/tts-mcp-server
- Repository: https://github.com/RTY2345RR/miragea-voice-mcp
- Website: https://miragea.ai/
- Changelog RSS feed: https://verifymcp.io/servers/rty2345rr-tts-mcp-server/tts-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/rty2345rr-tts-mcp-server/tts-mcp-server/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/rty2345rr-tts-mcp-server/tts-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/rty2345rr-tts-mcp-server/tts-mcp-server
