{"$schema":"https://modelcontextprotocol.io/schema/server-card.json","serverInfo":{"name":"audiopod-ai","version":"1.0.0","title":"AudioPod AI","description":"All-in-one AI audio workstation: stem separation, voice cloning, TTS, music generation, transcription, audiobook narration, and a browser DAW.","vendor":"AudioPod AI","homepage":"https://audiopod.ai","documentation":"https://api.audiopod.ai/docs","contact":"support@audiopod.ai"},"transport":{"type":"streamable-http","endpoint":"https://mcp.audiopod.ai","protocolVersion":"2025-06-18"},"authentication":{"type":"oauth2","metadata":"https://audiopod.ai/.well-known/oauth-protected-resource","scopesRequired":["audio:read","audio:write"]},"capabilities":{"tools":{"listChanged":true},"resources":{"subscribe":false,"listChanged":false},"prompts":{"listChanged":false},"logging":{}},"tools":[{"name":"generate_music","description":"Generate a song, instrumental, vocal-only stem, or rap track from a text caption."},{"name":"text_to_speech","description":"Synthesize speech from text in 100+ languages and 100+ voices."},{"name":"clone_voice","description":"Clone a voice from a 5–30s reference clip and reuse it for TTS."},{"name":"separate_stems","description":"Split audio into vocals, drums, bass, guitar, piano, other (up to 16 stems)."},{"name":"transcribe_audio","description":"Transcribe audio with speaker diarization and word-level timestamps."},{"name":"denoise_audio","description":"Remove background noise / room tone from speech recordings."},{"name":"convert_media","description":"Convert audio or video between formats (mp3/wav/flac/ogg/m4a, mp4/mov)."},{"name":"separate_speakers","description":"Isolate each speaker into a separate track from multi-speaker recordings."},{"name":"change_voice","description":"Convert a recording to a different target voice (voice-to-voice)."}]}