What it does
TTSForFree exposes AI voice generation to MCP clients. It offers text-to-speech, multi-voice podcast audio, voiceovers from subtitle files, speech-to-text transcription and video dubbing into several languages. Output is returned as hosted MP3 URLs, with thousands of voices across more than 100 languages. The server provides 21 tools, including voice search, favourites, custom voice design, account status and job polling.
It suits tasks such as turning an article or lesson into narration, producing a two-host podcast from one text, voicing a translated SRT file, transcribing a video into an SRT file, or dubbing a video into multiple languages after a credit estimate. Users who want a custom voice can describe it in text and have it created.
The server is hosted remotely, so nothing is installed locally. It is added as a custom connector in Claude or as an MCP server in other clients. Sign-in uses OAuth, and clients without OAuth support can use an API key header. Jobs run asynchronously: the client polls a status tool until the job reaches SUCCESS. Uploaded media and text are processed only to produce the requested output, and OAuth access can be revoked from the TTSForFree profile.
Limitations and requirements
A TTSForFree account is required. Sign-in uses OAuth, or an X-API-Key header for clients without OAuth support. A free plan is included, but paid generation consumes TTSForFree credits. Local video or audio uploads are limited to 2 GB per upload URL. Job tools are asynchronous and must be polled until SUCCESS.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
TTSForFree
Generate AI voices, text-to-speech, subtitles, transcription, and video localization.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it