$ loading_
Access text-to-speech, speech-to-text, and voice management via ElevenLabs API.
This MCP tool claims to provide speech features via the ElevenLabs API, which likely implies remote data exchange during normal use. However, the materials are sparse, and the stated 'no credentials/no remote endpoint' conflicts with the described functionality, so it warrants caution rather than an automatic high-risk rating.
The material states there are no keys/environment variables, but the feature description says it works 'via ElevenLabs API', which normally involves external service authentication. The documentation is insufficient to confirm fully anonymous access, so credential requirements may be incomplete or unclear.
Although the 'remote endpoint host' is listed as none, the description explicitly says it works via the ElevenLabs API for TTS/STT/voice management. This indicates that user text, audio, or voice configuration will likely be sent to ElevenLabs-related services, but the exact egress targets and scope are not documented.
The objective check shows it has executes-code capability, meaning it runs as a local MCP server/process. This is a normal property for such tools, and the provided material does not show any unusual system privileges beyond what its speech features would typically require.
The material does not claim any need to read/write local files, access sensitive directories, or request extra data permissions. Based on the available information, its data access surface appears limited to speech-related input/output, with no clear signs of overbroad access.
A positive factor is that the source is publicly available on GitHub, which helps auditability. However, it comes from a third-party registry, has 0 stars, no declared license, and unknown maintenance status, so community validation and maintenance signals are weak; review code and dependencies in an isolated environment first.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "ElevenLabs MCP Server" yet — see the docs or source repo.
Use ElevenLabs to convert the following script into natural-sounding English narration and return an audio file or playable result: "Welcome to our new product. This update focuses on improving performance and usability."
A natural-sounding narration audio clip suitable for demos, videos, or podcasts.
Use ElevenLabs to transcribe this meeting recording into English text, organized by speaker order; include timestamps if available.
A structured transcript of the recording for easier meeting note preparation.
List the currently available ElevenLabs voices, recommend three suitable for a tech product promo, and generate preview audio for the same script with each one.
A list of available voices, recommendation reasons, and preview outputs for each selected voice.
Generate speech, clone voices, transcribe audio, and create sound effects.
Clone custom voices for AI assistants and generate playable speech inline.
Adds speech recognition and text-to-speech for converting audio and text.
Convert text to speech via one interface with local and cloud engines.
Convert text into speech with Google TTS, voices, and style templates.
Convert speech into text for note-taking, organization, and analysis.