Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Simplified voice descriptions — no internal model references
What This Skill Does
AudioPod AI is an API for audio processing covering music generation (songs, rap, instrumentals, samples), stem separation up to 16 tracks, text-to-speech with voice cloning, noise reduction, speech-to-text transcription, and speaker diarization. It accepts audio files or URLs and returns downloadable output files.
Combines music generation, stem separation, TTS, transcription, and noise reduction in one pay-as-you-go API instead of requiring separate specialized services for each task.
When to use it
- Generate a lo-fi hip hop instrumental from a text prompt
- Isolate vocals from a song to create a karaoke track
- Transcribe a podcast recording with per-speaker labels
- Remove background noise from a recorded meeting
- Convert article text to speech using a cloned voice
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Separate the vocals from this YouTube video and transcribe what is being sung
- 1Submit the YouTube URL to the stem extraction endpoint with mode 'single' and stem 'vocals'
- 2Poll the job status until COMPLETED and retrieve the vocals download URL
- 3Submit the same YouTube URL to the transcription endpoint with word timestamps enabled
- 4Poll the transcription job until COMPLETED and retrieve the segment data
- 5Return the vocals audio URL alongside the timestamped lyric transcript
Download URL for the isolated vocal track and a timestamped transcript of the lyrics
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.