Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Paxa Labs

NPM · @PAXALABS/MCP

Thai, English, Mandarin speech AI: TTS with playback, transcription, translation, OCR, extraction

Available components

0 this week 81 Trust /100

Last scanned (18 hours ago)

Scores higher than 69% of npm servers

Category AI and Machine Learning

Trust breakdown (7 categories)

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 Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
  • 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
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 13 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability60
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 10214 tokens (~486/item across 21 items; 21 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 Management93
  • Stability check failed: the tool surface changed between 0.1.0-beta.15 and 0.1.0-beta.19: 1 tool removals, 0 breaking changes, 8 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 99% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 22 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
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 15 Nov 26 0
    • Package version: 0.1.0-beta.13 → 0.1.0-beta.19 functional
  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93.

  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 86.

  • 9 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 76 to 80.

  • 8 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 7 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
    • Security disclosure: pass → unverified ▼ functional
    • Package version: 0.1.0-beta.18 → 0.1.0-beta.19 functional
  • 5 Nov 26 0
    • Schema quality: 446 → 498 ▼ functional
    • Package version: 0.1.0-beta.17 → 0.1.0-beta.18 functional
  • 4 Nov 26 −4

    No change was recorded against any check on this day. Stability & Change Management went from 92 to 63.

Diagnostics

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 21 Nov 2026 · Analysed npm/@paxalabs/mcp@0.1.0-beta.19

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 92 packages
Packages resolved 92
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 21 exposed · ~9,289 tokens

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 →

Tool Tokens
control_playback ~131

Inspect and control the shared audio queue that speak, queue_speech, play_audio, and the voice design tools play through. status reports what is playing, what is queued, and any synthesis failures. pause holds playback until resume or clear, and audio queued meanwhile waits; pause is not supported on Windows, where skip or clear stops playback instead. skip drops the current segment and is refused when nothing is playing. clear stops playback and discards every queued segment, which must be queued again to be heard; audio files already written stay on disk. Free (no API call).

NameTypeReqDescription
actionstringyes–

No output schema declared.

No examples provided.

delete_voice ~130

Delete one of the account's designed voices and free its slot. The id is the voice_ id list_voices shows; it is looked up first, so an id the account does not have is answered without deleting anything, and catalog voices cannot be deleted. Cannot be undone: every later request in the voice fails, and designing again does not bring the same sound back. Use it only when the user asks to delete that voice; to change only its name, use rename_voice. Free.

NameTypeReqDescription
idstringyesThe designed voice's id (voice_...), from list_voices or save_voice

No output schema declared.

No examples provided.

design_voice ~239

Make a new voice from a written description and play the line it speaks through this machine's speakers. Use it when the user wants a voice the catalog does not have. Describe who is speaking and how they sound in one or two sentences: age, gender, role, pitch and texture, pace and manner, where it will be heard, and the language it speaks (a designed voice speaks one language: the one the description names, otherwise the one it is written in), such as "A calm Bangkok pharmacist in her thirties who explains dosages slowly and kindly, speaking Thai". Leave out real people's names, sound effects, and what the voice should say. The result is a draft, not yet a voice: refine_voice changes it, save_voice keeps it. Costs 5 credits per call, the line included; a retry designs again and is charged again.

NameTypeReqDescription
descriptionstringyesWho the voice is and how it sounds, in English, Thai, or Chinese, up to 1000 characters
playboolean–Play the voice's line out loud (default true). The line is saved to a file either way.

No output schema declared.

No examples provided.

dialogue_to_speech ~1,359

Synthesize a script of lines, each in its own voice, into one audio file without playing it: podcasts, interviews, radio plays, lessons and phone flows with more than one speaker. Pass the lines in speaking order with a voice each; gap_ms of silence goes between lines. For a single voice use text_to_speech; to hear a conversation now, call queue_speech once per line in that line's voice; play_audio plays the saved file. The file goes to output_path, replacing a file already there, or to a new timestamped name in PAXA_OUTPUT_DIR. A script over 100 lines or 20000 characters is sent in parts split between lines and joined with the same gap (mp3, opus, and wav need ffmpeg for that). Returns each line's start and end in the audio. With subtitles set, an srt or vtt caption file is written next to the audio, and no cue spans two lines. If synthesis fails partway, the lines already delivered whole, which were paid for, are saved and the result names the line to resume from. Costs the same as text_to_speech for the characters of every line: 10 credits per 1000, 12.5 with subtitles, 12.5 for a line in a designed voice (voice_...), 15 with both; the gap is free. Direction tags (paxa-tts-flash-v2, every voice): words in square brackets written into the text set the delivery from that point on, in English, Thai, or Chinese, e.g. [whispering], [speaking slowly, close to the microphone], [sad:0.5], or a blend [happy:0.7+sad:0.3]; [neutral] returns to the voice's own delivery. Sounds such as [laughs], [sighs], [gasps] play where written; [um] and [hmm] are spoken; <emph>...</emph> and <whisper>...</whisper> mark a span. [short pause], [pause], and [long pause] add silence after the word before them, and [pause 300ms] an exact length up to 500 ms. Nothing in brackets is spoken, tag characters bill as text, and a tag the model cannot do is refused before any charge. On paxa-tts-flash-v1 only khanomchan and kaprao read tags, from a fixed emotion list, and no voice reads pause tags.

NameTypeReqDescription
formatstring–Audio format (default "mp3"). opus is the smallest, wav is uncompressed 16-bit with a header, pcm is the same samples raw (little-endian mono, no header) for voice agents and audio pipelines, and mul…
gap_msinteger–Silence between one line and the next, in milliseconds (default 300). For a pause inside a line, write a pause tag.
languagestring–How codes, digits, and symbols are read: "th", "en", or "zh". Words keep the language of their script. Default "auto" works it out from the text; set it when a code such as AB2039 should be spelled i…
linesarrayyesThe lines in speaking order, up to 2000 lines and 200000 characters in all, at most 20000 in one line. Give each speaker a voice of their own. Recommended for general use: foithong (female) and massa…
modelstring–"paxa-tts-flash-v2" (default) has 50 voices that each speak Thai, English, and Mandarin, and every one reads direction tags written into the text. Pick "paxa-tts-flash-v1" only for its legacy feature…
output_pathstring–Where to save the file. Relative paths resolve against PAXA_OUTPUT_DIR (or the working directory).
sample_ratenumber–Sample rate of pcm or wav in Hz (default 24000): 8000, 16000, 22050, 24000, 32000, 44100, 48000 on paxa-tts-flash-v2; paxa-tts-flash-v1 serves 24000 only. Other formats have a fixed rate (8000 for mu…
speednumber–Speaking rate from 0.5 to 1.5 as a multiplier on the voice's design speed (1 is as designed; 1.2 to 1.3 suits long reads). Pitch is preserved and the price is the same. Defaults to PAXA_DEFAULT_SPEED…
subtitle_line_charsinteger–Columns per subtitle line, 10 to 120 (default 60, or 32 when the words are mostly Chinese, Japanese, or Korean). A Chinese, Japanese, or Korean character or full-width punctuation mark takes two colu…
subtitlesstring–Also write a caption file (same name as the audio, .srt or .vtt) timed from the synthesized words. Cues break at sentence punctuation, at pauses, and at the line budget, never inside a word and never…
temperaturenumber–How much the reading (pacing, pauses, breaths, melody) varies from one request to the next, 0 to 2, rounded to the nearest 0.1 (default 0.5). 0 gives the most repeatable reading, such as a line regen…

No output schema declared.

No examples provided.

extract_fields ~824

Extract typed fields from a local PDF, PNG, JPEG, or WebP document (up to 20 pages and 10 MiB) with Paxa Document Extraction. You write a schema of fields; every value returned is text printed in the document, read as the field's type, or null with the reason. Nothing is inferred or looked up. Built for Thai documents (receipts, tax invoices, forms, IDs) and fine on English ones. Use ocr_document instead for a document's full text. Returns a status line, the fields as JSON (null where a value is not printed), then the missing, unverified, truncated, and assumed fields. Costs 13 credits per page for a schema of up to 50 leaf fields and 19.5 per page for 51 to 100; the page reading and the evidence spans cost nothing extra. A schema the API refuses costs nothing and names the field and reason. The schema parameter summarizes the dialect; https://paxalabs.com/docs/extraction has every type and key.

NameTypeReqDescription
file_pathstringyesPath to a local PDF, PNG, JPEG, or WebP file
include_evidenceboolean–Also return, per field path, the printed span the value was read from. Free.
include_pagesboolean–Also return each page's text as Markdown, the reading the fields came from. Free.
output_pathstring–Save the full JSON response here. Relative paths resolve against PAXA_OUTPUT_DIR (or the working directory). An existing file is never overwritten.
schemaobjectyesPrefer the most specific type for each field: a specific type verifies the printed value (a date must parse, a thai_id must pass its check digit, a bank must be a real bank) and returns a normalized…

No output schema declared.

No examples provided.

get_account ~69

Show the account behind the API key or sign-in, read from the API on each call: credit balance, spending cap, plan, and rate limits. Call it before a large paid job, or after a call fails for credits or a rate limit; prices per model are in list_models. Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_models ~73

List the available Paxa models (speech, transcription, realtime transcription, translation, OCR, and extraction) with their limits and credit pricing, and the languages translate writes. Call it to check a limit or a price before a large job; voices are in list_voices, and the credit balance in get_account. Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_voices ~108

List the Paxa TTS voices in one response (no paging): recommended voices first, the account's designed voices with their slots, then the catalog roster per model with ids, names, gender, language, and character notes. Call it when the user asks what voices exist or wants a different one, and before save_voice to see free slots; pass an id from it as voice to speak, queue_speech, or text_to_speech. The default voice needs no lookup. Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

listen ~387

Record one spoken turn from this machine's microphone and return its transcript (Thai, English, Mandarin Chinese, or another language, code-switching included). Paxa's realtime transcription detects when the user starts and stops talking, so the call returns as soon as the turn ends; the audio goes straight to the API and nothing is written to disk. Waits for any speech this server is playing to finish first. Use it after speak when you asked the user a question and want their spoken answer; for a recording already on disk, use transcribe_audio instead. Returns an empty transcript when nobody spoke within wait_seconds. Costs 12.5 credits per minute of audio sent, silence included (a few seconds of listening costs well under one credit). Needs a microphone recorder on this machine (ffmpeg or sox; parecord or arecord on Linux) and Node 22 or newer; the host app must have microphone permission.

NameTypeReqDescription
conventionstring–"spoken" (default) writes numbers as said; "written" uses numerals. Only Thai is respelled.
languagestring–The language the speech is expected in, as a BCP 47 tag such as "th", "en", or "zh". A hint, not a filter: other languages are still written as spoken. Omit to auto-detect; set it when detection pick…
max_secondsinteger–Stop and return whatever was heard after this many seconds (default 30)
stylestring–"verbatim" (default) keeps fillers and false starts; "clean" drops them
vocabularyarray–Keyword pinning, as in transcribe_audio. Added to any configured PAXA_VOCABULARY terms.
wait_secondsinteger–Give up when nobody has started speaking after this many seconds (default 15)

No output schema declared.

No examples provided.

ocr_document ~183

Run Paxa OCR on a local PDF, PNG, JPEG, or WebP file and return its content as GitHub-flavored Markdown (or structured blocks). Reads Thai, English, Simplified Chinese, and other languages as printed, pages that mix them included, with no language setting; text set in two columns reads column by column. output "structured" returns typed blocks as JSON instead of Markdown. Use extract_fields instead for specific values (a total, a date, an ID number) checked and typed against a schema. Up to 50 pages and 10 MiB per file. Costs 6.5 credits per page.

NameTypeReqDescription
file_pathstringyesPath to a local PDF, PNG, JPEG, or WebP file
outputstring–"markdown" (default) returns prose; "structured" returns typed blocks as JSON

No output schema declared.

No examples provided.

play_audio ~169

Play a local audio file through this machine's speakers, for example a file produced earlier by text_to_speech. Waits for the audio playing now, plays ahead of queued long-form speech, and blocks until the file ends; control_playback skip or clear stops it early. Fails without playing when the file is missing, is not a playable format, or no audio player is installed; raw pcm, mulaw, and alaw files have no header and cannot be played. To say new text, use speak instead. Free (no API call).

NameTypeReqDescription
file_pathstringyesPath to a local audio file (mp3, wav, opus, ogg, flac, m4a, aac, aiff, caf), absolute or relative to the server's working directory

No output schema declared.

No examples provided.

queue_speech ~924

Read long content aloud (stories, articles, books). Splits the text into segments, synthesizes ahead while playing, and returns at once with the segment count and the estimated credits; segments play in order after anything already queued. There is no handle: control_playback monitors and controls the whole queue. Use speak instead for one short line that should play now and wait, and text_to_speech for a file without playback. Costs 10 credits per 1000 characters, 12.5 in a designed voice (voice_...). Direction tags (paxa-tts-flash-v2, every voice): words in square brackets written into the text set the delivery from that point on, in English, Thai, or Chinese, e.g. [whispering], [speaking slowly, close to the microphone], [sad:0.5], or a blend [happy:0.7+sad:0.3]; [neutral] returns to the voice's own delivery. Sounds such as [laughs], [sighs], [gasps] play where written; [um] and [hmm] are spoken; <emph>...</emph> and <whisper>...</whisper> mark a span. [short pause], [pause], and [long pause] add silence after the word before them, and [pause 300ms] an exact length up to 500 ms. Nothing in brackets is spoken, tag characters bill as text, and a tag the model cannot do is refused before any charge. On paxa-tts-flash-v1 only khanomchan and kaprao read tags, from a fixed emotion list, and no voice reads pause tags.

NameTypeReqDescription
languagestring–How codes, digits, and symbols are read: "th", "en", or "zh". Words keep the language of their script. Default "auto" works it out from the text; set it when a code such as AB2039 should be spelled i…
modelstring–"paxa-tts-flash-v2" (default) has 50 voices that each speak Thai, English, and Mandarin, and every one reads direction tags written into the text. Pick "paxa-tts-flash-v1" only for its legacy feature…
speednumber–Speaking rate from 0.5 to 1.5 as a multiplier on the voice's design speed (1 is as designed; 1.2 to 1.3 suits long reads). Pitch is preserved and the price is the same. Defaults to PAXA_DEFAULT_SPEED…
temperaturenumber–How much the reading (pacing, pauses, breaths, melody) varies from one request to the next, 0 to 2, rounded to the nearest 0.1 (default 0.5). 0 gives the most repeatable reading, such as a line regen…
textstringyesText to read aloud, Thai, English, or Mandarin Chinese
voicestring–Voice id from list_voices (default "foithong"), or a designed voice's id (voice_...) from save_voice, which speaks only on paxa-tts-flash-v2. Recommended for general use: foithong (female) and massam…

No output schema declared.

No examples provided.

refine_voice ~218

Change a draft voice in words and play its new line. The instruction says what to change, such as "a little lower and slower" or "warmer, and older"; the rest of the voice stays, so change one quality at a time. Each call returns a new draft handle and the earlier handles keep their versions, so the user can go back to one. save_voice keeps the draft the user picks. Refining never changes a voice already saved: saving a refined draft makes another voice, and rename_voice changes only a name. Costs 5 credits per call, the line included; a retry refines again and is charged again.

NameTypeReqDescription
draftstringyesA draft handle that design_voice or refine_voice printed (such as "draft-2"), or a draft string from the Paxa console.
instructionstringyesWhat to change about the voice, up to 500 characters
playboolean–Play the voice's line out loud (default true). The line is saved to a file either way.

No output schema declared.

No examples provided.

rename_voice ~135

Rename one of the account's designed voices, given its voice_ id from list_voices or save_voice. The id and the sound stay the same, so anything that uses the id keeps working. The new name takes 1 to 60 characters, and a catalog voice's name is refused. To change how a voice sounds, refine a draft and save it as a new voice; to remove one, use delete_voice. Free.

NameTypeReqDescription
idstringyesThe designed voice's id (voice_...), from list_voices or save_voice
namestringyesThe new name, up to 60 characters

No output schema declared.

No examples provided.

save_voice ~208

Save a draft from design_voice or refine_voice as one of the account's voices, and get its id (voice_...), which speak, queue_speech, and text_to_speech accept as voice on paxa-tts-flash-v2, for this account only. Save only the draft the user picked. Saving the same draft again returns the same voice and uses no slot. A saved voice's sound never changes: design a new voice for a different sound. The plan sets how many voices the account keeps (Free 1, Starter 3, Standard 10, Pro 50); list_voices shows the slots in use. Free.

NameTypeReqDescription
draftstringyesA draft handle that design_voice or refine_voice printed (such as "draft-2"), or a draft string from the Paxa console.
namestring–A name for the voice, up to 60 characters (default: the name the design gave it). A catalog voice's name is refused.

No output schema declared.

No examples provided.

send_feedback ~248

Report a wrong or poor output, an API problem, or a platform issue to the Paxa Labs team, tied to the request ids the other tools print ("Request id: ..."). A rating alone on at least one request id is a complete report. For a wrong output, add an example with the exact input, the output received, and the output expected. Returns the report's id once it is filed. Free, no credits. Use it when the user says an output was wrong, or asks to report a problem; do not file reports the user did not ask for.

NameTypeReqDescription
exampleobject–A worked case: the exact input, the output received, and the output expected
kindstringyes"model" for a wrong or poor output, "api" when the API misbehaved, "platform" for dashboard, billing, or docs, else "other"
messagestring–What happened and what was expected, plain text or Markdown
ratingstring–Judgment of the output the request ids name
request_idsarray–Up to 20 request ids from earlier tool results, or a live session's connection id

No output schema declared.

No examples provided.

sign_in ~191

Connect this machine to the user's Paxa account when no API key is configured: opens the Paxa sign-in page in the user's browser with a code filled in, and the user approves there (new accounts include free credits). Every Paxa tool then works, in every session on this machine, until the user signs out or leaves it unused for 30 days. Waits up to wait_seconds for the approval; if it has not come yet, call sign_in again to keep waiting on the same code. When no browser opens, it returns the page and the code at once for you to give the user. Answers at once when already signed in or when PAXA_API_KEY is set. Free.

NameTypeReqDescription
wait_secondsinteger–How long to wait for the approval before returning (default 50). The sign-in keeps waiting in the background either way, until its code expires after 30 minutes.

No output schema declared.

No examples provided.

speak ~890

Synthesize a short line with Paxa TTS and play it through this machine's speakers. Blocks until playback finishes. Waits for the currently playing audio but jumps ahead of queued long-form segments. For long content use queue_speech. Costs 10 credits per 1000 characters, 12.5 in a designed voice (voice_...). Direction tags (paxa-tts-flash-v2, every voice): words in square brackets written into the text set the delivery from that point on, in English, Thai, or Chinese, e.g. [whispering], [speaking slowly, close to the microphone], [sad:0.5], or a blend [happy:0.7+sad:0.3]; [neutral] returns to the voice's own delivery. Sounds such as [laughs], [sighs], [gasps] play where written; [um] and [hmm] are spoken; <emph>...</emph> and <whisper>...</whisper> mark a span. [short pause], [pause], and [long pause] add silence after the word before them, and [pause 300ms] an exact length up to 500 ms. Nothing in brackets is spoken, tag characters bill as text, and a tag the model cannot do is refused before any charge. On paxa-tts-flash-v1 only khanomchan and kaprao read tags, from a fixed emotion list, and no voice reads pause tags.

NameTypeReqDescription
languagestring–How codes, digits, and symbols are read: "th", "en", or "zh". Words keep the language of their script. Default "auto" works it out from the text; set it when a code such as AB2039 should be spelled i…
modelstring–"paxa-tts-flash-v2" (default) has 50 voices that each speak Thai, English, and Mandarin, and every one reads direction tags written into the text. Pick "paxa-tts-flash-v1" only for its legacy feature…
speednumber–Speaking rate from 0.5 to 1.5 as a multiplier on the voice's design speed (1 is as designed; 1.2 to 1.3 suits long reads). Pitch is preserved and the price is the same. Defaults to PAXA_DEFAULT_SPEED…
temperaturenumber–How much the reading (pacing, pauses, breaths, melody) varies from one request to the next, 0 to 2, rounded to the nearest 0.1 (default 0.5). 0 gives the most repeatable reading, such as a line regen…
textstringyesText to speak, Thai, English, or Mandarin Chinese, up to 2000 characters
voicestring–Voice id from list_voices (default "foithong"), or a designed voice's id (voice_...) from save_voice, which speaks only on paxa-tts-flash-v2. Recommended for general use: foithong (female) and massam…

No output schema declared.

No examples provided.

text_to_speech ~1,376

Synthesize speech with Paxa TTS and save it as an audio file without playing it: voiceovers, narration, audiobooks, phone prompts. To hear speech instead, use speak (a short line) or queue_speech (long reads); play_audio plays a saved file later. The file goes to output_path, replacing a file already there, or to a new timestamped name in PAXA_OUTPUT_DIR. For several speakers in one file, use dialogue_to_speech. Text beyond 20000 characters is split at paragraphs and sentences and the parts are joined into one file (mp3, opus, and wav need ffmpeg for that). With subtitles set, an srt or vtt caption file that matches the voice word for word is written next to the audio. Costs 10 credits per 1000 characters, 12.5 with subtitles, 12.5 in a designed voice (voice_...), 15 with both; every format and sample rate costs the same. Direction tags (paxa-tts-flash-v2, every voice): words in square brackets written into the text set the delivery from that point on, in English, Thai, or Chinese, e.g. [whispering], [speaking slowly, close to the microphone], [sad:0.5], or a blend [happy:0.7+sad:0.3]; [neutral] returns to the voice's own delivery. Sounds such as [laughs], [sighs], [gasps] play where written; [um] and [hmm] are spoken; <emph>...</emph> and <whisper>...</whisper> mark a span. [short pause], [pause], and [long pause] add silence after the word before them, and [pause 300ms] an exact length up to 500 ms. Nothing in brackets is spoken, tag characters bill as text, and a tag the model cannot do is refused before any charge. On paxa-tts-flash-v1 only khanomchan and kaprao read tags, from a fixed emotion list, and no voice reads pause tags.

NameTypeReqDescription
formatstring–Audio format (default "mp3"). opus is the smallest, wav is uncompressed 16-bit with a header, pcm is the same samples raw (little-endian mono, no header) for voice agents and audio pipelines, and mul…
languagestring–How codes, digits, and symbols are read: "th", "en", or "zh". Words keep the language of their script. Default "auto" works it out from the text; set it when a code such as AB2039 should be spelled i…
modelstring–"paxa-tts-flash-v2" (default) has 50 voices that each speak Thai, English, and Mandarin, and every one reads direction tags written into the text. Pick "paxa-tts-flash-v1" only for its legacy feature…
output_pathstring–Where to save the file. Relative paths resolve against PAXA_OUTPUT_DIR (or the working directory).
sample_ratenumber–Sample rate of pcm or wav in Hz (default 24000): 8000, 16000, 22050, 24000, 32000, 44100, 48000 on paxa-tts-flash-v2; paxa-tts-flash-v1 serves 24000 only. Other formats have a fixed rate (8000 for mu…
speednumber–Speaking rate from 0.5 to 1.5 as a multiplier on the voice's design speed (1 is as designed; 1.2 to 1.3 suits long reads). Pitch is preserved and the price is the same. Defaults to PAXA_DEFAULT_SPEED…
subtitle_line_charsinteger–Columns per subtitle line, 10 to 120 (default 60, or 32 when the words are mostly Chinese, Japanese, or Korean). A Chinese, Japanese, or Korean character or full-width punctuation mark takes two colu…
subtitlesstring–Also write a caption file (same name as the audio, .srt or .vtt) timed from the synthesized words: cues break at sentence punctuation, at pauses, and at the line budget, never inside a word, Thai inc…
temperaturenumber–How much the reading (pacing, pauses, breaths, melody) varies from one request to the next, 0 to 2, rounded to the nearest 0.1 (default 0.5). 0 gives the most repeatable reading, such as a line regen…
textstringyesText to synthesize, Thai, English, or Mandarin Chinese, up to 200000 characters
voicestring–Voice id from list_voices (default "foithong"), or a designed voice's id (voice_...) from save_voice, which speaks only on paxa-tts-flash-v2. Recommended for general use: foithong (female) and massam…

No output schema declared.

No examples provided.

transcribe_audio ~790

Transcribe a local recording or video of speech in Thai, English, Mandarin Chinese, or another language, code-switching included (mp3, wav including mu-law and A-law phone recordings, flac, ogg, m4a, aac, webm; or mp4, mov, mkv, avi and other video files, whose sound track is extracted locally with ffmpeg; up to 120 minutes and 95 MiB) with Paxa STT. The transcript comes back inline, so nothing needs to be read from disk afterwards; optionally it is also saved as txt, json (with word timings and segments), srt, or vtt, named after the recording. Existing files are never overwritten. Detects the language and can label speakers; nothing is translated. For one live answer from the microphone, use listen instead. Terms configured in PAXA_VOCABULARY or PAXA_VOCABULARY_FILE are pinned on every call. Costs 8.33 credits per minute of audio (0.1 minimum); subtitles and word timings cost nothing extra. Long recordings take minutes to process.

NameTypeReqDescription
conventionstring–"spoken" (default) writes numbers and dates as they were said; "written" uses numerals. Only Thai is respelled; other languages read the same under both.
diarizationboolean–Label speakers across the whole recording (slower to return). The transcript is then returned as one line per turn, and subtitle cues never cross a speaker change.
file_pathstringyesPath to a local recording (mp3, wav, flac, ogg, m4a, aac, webm) or video (mp4, mov, mkv, avi, and more)
languagestring–The language the speech is expected in, as a BCP 47 tag such as "th", "en", or "zh". A hint, not a filter: other languages are still written as spoken. Omit to auto-detect; set it when detection pick…
output_dirstring–Where to write the files. Defaults to the recording's own folder. A relative path resolves against PAXA_OUTPUT_DIR (or the working directory).
pauses_overnumber–List every silence between words at least this many seconds long, with its start and end: the dead air to cut when editing. 0.7 suits speech; 1.5 finds only the long gaps. Free (uses the word timings…
savearray–Files to write, named after the recording: txt (the transcript), json (text, words with timings, segments, usage), srt or vtt (subtitles rendered by the API). Omit to write nothing.
stylestring–"verbatim" (default) keeps fillers and false starts; "clean" drops them
subtitle_line_charsinteger–Columns per subtitle line, 10 to 120 (default 60, or 32 when the words are mostly Chinese, Japanese, or Korean). A Chinese, Japanese, or Korean character or full-width punctuation mark takes two colu…
timestampsboolean–Also return word-level timings inline as JSON (can be long). The json file always has them.
vocabularyarray–Keyword pinning: terms the recording likely contains, spelled the way they should appear in the transcript (product names, people, places, jargon; in any language). Up to 50 terms of 50 characters. T…

No output schema declared.

No examples provided.

translate ~637

Translate text into any of 15 languages, from any of them, with Paxa Translate: Thai (th), English (en), Chinese (zh), Japanese (ja), Korean (ko), Arabic (ar), French (fr), German (de), Hindi (hi), Indonesian (id), Malay (ms), Portuguese (pt), Russian (ru), Spanish (es), Vietnamese (vi). The source language is detected per segment, so mixed-language text works; a segment already in the target language comes back unchanged. Accepts one string or up to 200 segments that share context, and returns each translation (numbered for segments) with its detected source language, any review flag, and the credits used. For text in a PDF or image, run ocr_document first. Costs 25 credits per 1000 text characters per rendering (minimum 2 credits), so 1000 characters cost 25 credits, or 50 with alternatives 2; instructions, context, examples, do_not_translate strings, and glossary terms bill at 8 per 1000.

NameTypeReqDescription
alternativesinteger–Renderings per segment, best first (default 1). Each one bills the text again and counts against the 20,000-character text limit.
borrowed_wordsstring–How to render borrowed words: "auto" (default) uses the established form in the target language, "transliterate" writes them in the target script, "preserve" keeps technical terms and proper nouns in…
contextstring–Background that conditions the translation without being translated: the surrounding document, the domain, the audience
do_not_translatearray–Strings that must appear in the translation exactly as written
examplesarray–Style examples: source sentences with their preferred translations, whose tone and phrasing the translation follows. Up to 100 pairs.
formalitystring–"auto" (default) matches the tone of the source; "formal" writes the target language's polite written register (polite particles in Thai, the polite form of address where a language has one); "casual…
formatstring–Treat input as plain text, Markdown, or HTML; only the prose of Markdown and HTML is translated, links, code, and tags come back untouched
glossaryarray–Term pairs the translation must use, applied in context (inflected and placed grammatically). Send the whole glossary: terms whose source does not appear in the text are dropped before the request ru…
instructionsstring–Free-form direction for the translator: tone, audience, house rules, terminology. Style only.
sourcestring–Pin the source language only when detection gets it wrong (default "auto", detected per segment). Must differ from target.
targetstringyesThe language to write, as its code (see the description). Chinese ("zh") is written in Simplified characters.
text–yesText to translate: one string, or an array of segments translated together

No output schema declared.

No examples provided.

Install

How do I install the Paxa Labs MCP server?

Paxa Labs runs locally as an npm package, launched with npx -y @paxalabs/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @paxalabs/mcp

# add to Claude Code
claude mcp add com-paxalabs-mcp -- npx -y @paxalabs/mcp
Common questions

What is the Paxa Labs MCP server?

Paxa Labs is an MCP server listed in the public MCP registry as com.paxalabs/mcp. Thai, English, Mandarin speech AI: TTS with playback, transcription, translation, OCR, extraction. This page covers its npm package (@paxalabs/mcp).

Is the Paxa Labs MCP server safe to use?

Paxa Labs scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 Paxa Labs MCP server expose?

Paxa Labs exposes 21 tools: speak, queue_speech, control_playback, play_audio, text_to_speech, and 16 more. Their descriptions and schemas cost roughly 9,289 tokens of context every time the server is loaded.

Is the Paxa Labs MCP server still maintained?

Paxa Labs 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 Paxa Labs MCP server under?

Paxa Labs 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 Paxa Labs MCP server?

VerifyMCP ran 16 checks on Paxa Labs, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.