{"protocolVersion":"0.3.0","name":"AudioPod AI Audio Agent","version":"1.0.0","description":"Production AI agent for end-to-end audio production: music generation, voice cloning, TTS, stem separation, transcription, audiobook narration, podcast creation, and DAW automation.","url":"https://api.audiopod.ai/api/v1/agent/chat","provider":{"organization":"AudioPod AI","url":"https://www.audiopod.ai"},"iconUrl":"https://www.audiopod.ai/web-app-manifest-512x512.png","documentationUrl":"https://api.audiopod.ai/docs","supportedInterfaces":[{"url":"https://api.audiopod.ai/api/v1/agent/chat","transport":"JSONRPC","protocol":"https"},{"url":"https://api.audiopod.ai/api/v1/mcp","transport":"MCP","protocol":"https"}],"defaultInputModes":["text/plain","application/json"],"defaultOutputModes":["text/plain","application/json","text/event-stream","audio/wav","audio/mpeg"],"capabilities":{"streaming":true,"pushNotifications":false,"stateTransitionHistory":true},"securitySchemes":{"oauth2":{"type":"oauth2","flows":{"password":{"tokenUrl":"https://api.audiopod.ai/api/v1/auth/token","refreshUrl":"https://api.audiopod.ai/api/v1/auth/refresh","scopes":{"audio:read":"Read audio assets","audio:write":"Create or modify audio assets"}}}},"apiKey":{"type":"apiKey","in":"header","name":"X-API-Key"}},"security":[{"oauth2":["audio:read","audio:write"]},{"apiKey":[]}],"skills":[{"id":"generate_music","name":"Generate Music","description":"Compose a full song from a text prompt (style, lyrics, BPM, duration).","tags":["music","generation"],"examples":["Generate a 90 BPM lo-fi hip hop track with rainy ambient pads, 60 seconds.","Make a Bollywood pop anthem with Hindi lyrics about chasing dreams."]},{"id":"synthesize_speech","name":"Text-to-Speech","description":"Synthesize speech from text in 100+ languages with 100+ voices, including SSML control.","tags":["tts","voice","speech"]},{"id":"clone_voice","name":"Voice Cloning","description":"Clone a voice from a 5–30s reference clip and reuse it for narration.","tags":["voice-clone","voice","narration"]},{"id":"separate_stems","name":"Stem Separation","description":"Split a song into vocals, drums, bass, guitar, piano, and up to 16 fine-grained stems.","tags":["stems","vocal-removal","karaoke"]},{"id":"transcribe_audio","name":"Transcription","description":"Transcribe audio with speaker diarization and word-level timestamps.","tags":["transcription","stt","diarization"]},{"id":"denoise_audio","name":"Noise Reduction","description":"Remove background noise, hum, and reverb from speech recordings.","tags":["noise-reduction","cleanup"]},{"id":"generate_audiobook","name":"Audiobook Studio","description":"Convert PDF/EPUB/DOCX manuscripts into ACX-compliant audiobooks with multi-voice narration.","tags":["audiobook","narration","acx","kindle-vella"]},{"id":"generate_podcast","name":"Podcast Studio","description":"Turn documents and articles into multi-speaker AI podcast conversations.","tags":["podcast","notebooklm-alternative"]}]}