{"schema_version":"v1","name_for_human":"AudioPod AI","name_for_model":"audiopod","description_for_human":"Generate music and speech, clone voices, split stems, and transcribe audio.","description_for_model":"AudioPod is an audio production API. Use it to generate music, synthesize or clone speech,\nseparate stems, split multi-speaker recordings by speaker, transcribe audio, remove noise,\nand convert media formats.\n\nCapabilities:\n- Text to Speech · powered by AudioSonic: AudioSonic is AudioPod's text-to-speech engine: natural, studio-grade narration with inline emotion directing, timed pauses, IPA pronunciation control, and optional word-level timestamps.\n- Voice Cloning · powered by AudioSonic: Voice cloning runs on the AudioSonic engine — clone a voice from a 5–30s reference clip and reuse it for narration or TTS across the same language reach as the premium voice engine.\n- Voice Design · powered by AudioSonic: Voice Design, part of the AudioSonic family, creates a brand-new voice from a plain-text description, previews candidates, and publishes one as a reusable voice.\n- Music Generation · powered by AudioMusic: AudioMusic is AudioPod's music generation engine: full songs, instrumentals, and rap with synchronized LRC lyrics, royalty-free for commercial use on paid plans.\n- Transcription · powered by AudioTranscribe: AudioTranscribe is AudioPod's speech-to-text engine: transcription with speaker diarization, word-level timestamps, and standard or premium accuracy, plus real-time streaming.\n- Speaker Separation · powered by AudioDiarize: AudioDiarize is AudioPod's speaker separation engine: it diarizes a multi-person recording and splits it into an individual audio track per speaker.\n- Stem Separation · powered by AudioStems: AudioStems is AudioPod's stem separation engine: split a song into vocals, drums, bass, guitar, piano and more, or isolate any of a 45-instrument catalog.\n- Audiobook Narration: End-to-end audiobook production: parse a PDF/EPUB/DOCX/TXT manuscript, auto-detect chapters, narrate, and export masters that meet ACX audio-file specifications.\n- Podcast Creation: Turn source documents or a topic into a podcast episode with one to four AI hosts and an editable script.\n- Audio Reader: Turn an article, URL, or long block of text into narrated audio with a shareable, embeddable player.\n- Noise Reduction: Remove background noise, hiss, hum, and room tone from a recording while preserving the voice character.\n- Media Conversion: Convert audio and video between all major formats (MP3, WAV, FLAC, OGG, M4A, AAC, and common video containers).\n- Audio Translation: Translate spoken audio into text in another language via the OpenAI-compatible translations endpoint.\n\nLong-running tools return a job_id immediately; poll check_job_status with that job_id until\nthe status is COMPLETED and read the output URLs from the result. Calls are prepaid from the\ndeveloper's API wallet, so a request can fail with an insufficient-balance error that the user\nresolves by topping up at https://audiopod.ai/dashboard/account/api-keys.","auth":{"type":"user_http","authorization_type":"bearer","instructions":"Create an API key at https://audiopod.ai/dashboard/account/api-keys and send it as `Authorization: Bearer ap_…`. New developer accounts get $1 of free API credit, granted once with the first API key on a verified email."},"api":{"type":"openapi","url":"https://api.audiopod.ai/api/v1/openapi.json","is_user_authenticated":true},"logo_url":"https://audiopod.ai/web-app-manifest-512x512.png","contact_email":"support@audiopod.ai","legal_info_url":"https://audiopod.ai/terms","x_audiopod":{"mcp":{"transport":"streamable-http","url":"https://mcp.audiopod.ai","protocolVersion":"2025-06-18","serverCard":"https://audiopod.ai/.well-known/mcp.json","tools":[{"name":"generate_music","description":"AudioMusic is AudioPod's music generation engine: original songs, beats and instrumentals from a description, with synced lyrics. AudioPod writes the lyrics unless the user supplies them."},{"name":"compose_music","description":"Write an editable score (melody, chords, sections) for a new song without recording it yet — for when the user wants to shape the tune first."},{"name":"revise_music_score","description":"Change a composed score in plain words (\"brighter chorus\", \"down a key\"); everything you did not ask to change is kept. Available when enabled for the account."},{"name":"record_music_score","description":"Record a score as a finished track, optionally with a new style or new words for the same tune."},{"name":"get_music_score","description":"Read the editable score of a track or composed score you own: key, meter, tempo, sections, length and the notation. Read-only."},{"name":"edit_music_score","description":"Deprecated alias of record_music_score: record a track from a complete replacement score."},{"name":"text_to_speech","description":"AudioSonic is AudioPod's text-to-speech engine: natural, studio-grade narration with inline emotion directing, timed pauses, IPA pronunciation control, and optional word-level timestamps."},{"name":"transcribe_audio","description":"AudioTranscribe is AudioPod's speech-to-text engine: transcription with speaker diarization, word-level timestamps, and standard or premium accuracy, plus real-time streaming."},{"name":"separate_stems","description":"AudioStems is AudioPod's stem separation engine: split a song into vocals, drums, bass, guitar, piano and more, or isolate any of a 45-instrument catalog."},{"name":"clone_voice","description":"Voice cloning runs on the AudioSonic engine: create a custom voice from a reference clip and reuse it for narration or text to speech. Only the user's own voice, or a voice whose speaker has given explicit permission; requests to clone a public figure or anyone else without consent are declined, and the user must confirm consent before cloning."},{"name":"denoise_audio","description":"Remove background noise, hiss, hum, and room tone from a recording while preserving the voice character."},{"name":"convert_media","description":"Convert audio and video between all major formats (MP3, WAV, FLAC, OGG, M4A, AAC, and common video containers)."},{"name":"separate_speakers","description":"AudioDiarize is AudioPod's speaker separation engine: it diarizes a multi-person recording and splits it into an individual audio track per speaker."},{"name":"change_voice","description":"Convert a recording into a different target voice, preserving the words and timing of the original performance."},{"name":"audio_to_midi","description":"Convert a recording of a melody, instrument or song into MIDI files (per-instrument MIDI plus one multitrack MIDI), for notation or DAW work."},{"name":"check_job_status","description":"Poll a long-running job by the job_id an earlier tool call returned, and read its status and finished output URLs."},{"name":"get_account","description":"Read the signed-in account's plan and credits left (monthly allowance and pay-as-you-go), with links to manage the account."},{"name":"get_profile","description":"Identify the connected account with a stable, opaque account id."}]},"documentation":"https://docs.audiopod.ai","pricing":"https://audiopod.ai/pricing"}}