Speechify MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Speechify MCP
A remote Model Context Protocol server for Speechify text-to-speech.
Tools
speechify_list_voices— list/filter available Speechify voices.speechify_generate_speech— generate audio from text or supported SSML.speechify_speak_uk_english— convenience tool using the Simba 3.2 English model.
Related MCP server: transcript-tts
Environment variables
Copy .env.example to .env.local for local development.
SPEECHIFY_API_KEY=...
MCP_ACCESS_TOKEN=...MCP_ACCESS_TOKEN is optional but strongly recommended for any public deployment. Clients should send it as a Bearer token to the MCP endpoint.
Never put the Speechify key into a browser/client config. It belongs only on the MCP server.
Local development
npm install
npm run devHealth check:
http://localhost:3000/api/healthMCP endpoint:
http://localhost:3000/api/mcpVercel
Deploy the project, then add SPEECHIFY_API_KEY and MCP_ACCESS_TOKEN as Vercel environment variables.
Your remote MCP URL will be:
https://YOUR-DOMAIN.vercel.app/api/mcpClient configuration
For an MCP client that supports remote Streamable HTTP, use the /api/mcp URL. If MCP_ACCESS_TOKEN is configured, send:
Authorization: Bearer YOUR_MCP_ACCESS_TOKENNotes
The MCP intentionally does not expose Speechify API credentials.
English speech defaults to
simba-3.2.Use
speechify_list_voicesfirst to choose a validvoice_id.Voice cloning is not included in v1 because it requires explicit verified consent and a multipart upload flow. It can be added separately if required.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Generate English and Chinese speech, split long text, track batch jobs, and download audio.
Remote text-to-speech MCP server with text_to_speech and list_voices tools. Free plan.
Synthesize short texts into WAV audio using offline formant voices in English, German and Spanish
Speech, transcription, voice agents, Trace, Recap, dubbing and narration with browser OAuth.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProfile-driven MCP server for Google Cloud Text-to-Speech that exposes tools to synthesize text to speech, run diagnostics, and stop playback, with voice and settings locked per profile.1MIT
- FlicenseAqualityDmaintenanceConverts text or transcripts into MP3 audio using Microsoft Edge's free neural voices. Provides text-to-speech and voice listing tools with no API key required.2-

audio.ditto/ttsofficial
FlicenseNot gradedqualityCmaintenanceEnables AI clients to browse voices and languages and synthesize text into downloadable audio links, including batch jobs of up to 1,000 texts.1-- AlicenseNot gradedqualityBmaintenanceEnables clients to synthesize text into audio in German, English, French, and Italian, choose voices and output formats, list available voices and formats, and delete cached audio files.Apache 2.0