$ loading_
Run local speech-to-text and text-to-speech with configurable engine switching.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "STT2TTS MCP" yet — see the docs or source repo.
Use STT2TTS MCP to transcribe /audio/team-sync.wav into Chinese text, grouped by speaker turns with timestamps.
A timestamped meeting transcript that is easy to review, summarize, or search.
Use STT2TTS MCP to convert the following product intro into natural Chinese speech and save it as a WAV file: 'Welcome to our new release. It supports faster speech recognition and synthesis.'
An audio file ready to play or embed in a presentation.
Explain how to switch the speech recognition and text-to-speech engines in STT2TTS MCP via config.yaml to another local engine, and provide validation steps.
A configuration guide and test steps for switching engines without changing code.
Convert text to speech via one interface with local and cloud engines.
Transcribe speech on Linux and inject text into Claude via Tmux.
Convert speech into text for note-taking, organization, and analysis.
Convert text into lifelike speech with customizable voice, rate, volume, and pitch.
Adds speech recognition and text-to-speech for converting audio and text.
Access text-to-speech, speech-to-text, and voice management via ElevenLabs API.