# Agent Data Tools Voice Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Agent Data Tools Voice

Transcribe voice notes and recordings, and turn text into spoken MP3 audio.

- Record: https://musedirectory.ai/connector/agent-data-tools-voice
- Category: Productivity
- Developer: Nutshell2000 (https://agent-data-tools.revmesh2074.workers.dev/)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 1115ms, checked 2026-11-15T18:15:57Z
- Endpoint: https://agent-data-tools.revmesh2074.workers.dev/mcp/voice
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-11-15T18:26:24Z)
- Source: Found in the official MCP Registry (io.github.Nutshell2000/agent-data-tools-voice) https://registry.modelcontextprotocol.io/v0/servers?search=io.github.Nutshell2000%2Fagent-data-tools-voice

Connects to Whisper and Deepgram to transcribe audio and video from a URL or upload, with optional SRT/VTT subtitles and timestamps, and to turn text into MP3 speech in English or Spanish. Muse can turn a voice memo into notes, summarize a meeting, or read a summary aloud. Each call is billed.

Example request: "Turn this voice memo into meeting notes with action items and a short summary."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Agent Data Tools Voice to help me. It is a free service with an MCP server at https://agent-data-tools.revmesh2074.workers.dev/mcp/voice. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- transcribe: Transcribe speech from an audio file at a public URL, or uploaded in a POST body, using Whisper large-v3-turbo. Returns the transcript text, detected language, duration and word count; subtitles=srt or vtt adds subtitle text and timestamps=true adds timed segments and words. Acce
- ai_speech: Turn up to 300 characters of text into natural, human-sounding speech as an MP3 (base64), in English (40 voices) or Spanish (10 voices), with Deepgram Aura-2. Pick a voice by name or leave the default. Use for voice replies, audio notes, accessibility and phone or chat bots; for 
- text_to_speech: Text to speech for a paragraph or a page: turn up to 2,000 characters of text into natural, human-sounding speech as one MP3 (base64), in English (40 voices) or Spanish (10 voices), with Deepgram Aura-2. Pick a voice by name or leave the default. Use for narration, article and su
- transcribe_long: Transcribe a podcast, meeting, interview or lecture: up to 60 minutes of MP3 or WAV (25 MB) by URL or uploaded in a POST body, 90+ languages, Whisper large-v3-turbo. Parts are joined, so subtitles=srt or vtt and timestamps=true cover the whole recording; longer audio is refused b
- transcribe_summary: Summarize a voice note, meeting, call or podcast in one call: transcribes up to 60 minutes (MP3/WAV up to 25 MB; M4A, OGG or WebM up to 5 MB) by URL or upload, then returns a title, summary, key points, action items with owner and due date, open questions and the transcript, in t
- text_to_speech_lite: Low-cost text to speech for longer English text: up to 2,000 characters as one MP3 (base64) with Deepgram Aura-1, 12 voices. Half the price per character of text_to_speech, with a slightly less natural voice. Pick a voice by name or leave the default. Use for narration drafts, re

Screening checks:
- MCP handshake: pass (Answered in 770ms)
- Domain against threat feeds (Cloudflare security DNS): pass (agent-data-tools.revmesh2074.workers.dev not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (6 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (Domain registered 2836 days ago)
- AI review of purpose and tool behavior: pass (per-call payment via USDC or card key, disclosed up front)