$ loading_
Convert speech and text with OpenAI-compatible transcription and synthesis APIs.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "ttsstt-mcp-server" yet — see the docs or source repo.
Use ttsstt-mcp-server to transcribe ./recordings/team-meeting.mp3 into Chinese text, preserve pauses, and save paragraph-formatted output to ./outputs/meeting-transcript.txt.
A transcript file of the meeting audio for notes, review, or further analysis.
Use ttsstt-mcp-server to convert this script into a natural female voice and save it to ./outputs/promo.wav: Welcome to our new product. It helps teams collaborate more efficiently every day.
A playable voiceover audio file suitable for promos, demos, or video narration.
Use ttsstt-mcp-server to batch process the ./audios folder: transcribe all .wav files into English text, and synthesize ./scripts/announcement.txt into a male voice, saving everything to ./outputs.
Batch transcription text files and synthesized audio files for automated content workflows.
Convert text to speech quickly and browse available voices and models.
Run local speech-to-text and text-to-speech with configurable engine switching.
Convert text into speech with Google TTS, voices, and style templates.
Convert text into natural-sounding speech audio through an MCP server.
Access text-to-speech, speech-to-text, and voice management via ElevenLabs API.
Transcribe speech on Linux and inject text into Claude via Tmux.