Audio Processing

Task progress is available through WebSocket. See Task Progress Query.

Gitruck Cloud audio processing APIs provide speech-to-text (ASR), noise reduction, silence removal, speaker diarization, audio separation, audio pitch & speed, music analysis, piano audio to MIDI, and piano audio enhancement capabilities.

General Notes

All audio processing APIs use an asynchronous task model:

  1. Upload file: Call the File Upload API to get a file_id. Supported formats include audio files (mp3, wav, m4a, etc.) and video files (mp4, etc., audio track extracted automatically).
  2. Create task: Call the corresponding processing API (POST) with the file_id to create a task and receive a task_id.
  3. Poll for result: Call the query API (GET) to poll the task status. Results are available when status becomes completed.

💡 Tip: Poll every 2–5 seconds.

API List

APIPathDescription
Speech to Text (ASR)/task/asrConvert audio to text with multilingual support and timestamps
Noise Reduction/task/audio_noise_reduceReduce background noise and enhance voice clarity
Silence Removal/task/audio_silence_removeRemove silence gaps to make audio more compact
Speaker Diarization/task/audio_speaker_splitIdentify speakers and archive them as separate audio tracks
Audio Separation/task/audio_separationSeparate vocals from accompaniment into independent tracks
Audio Pitch & Speed/task/audio_stretchAdjust pitch and playback speed independently
Music Analysis & Tagging/task/audio_music_analyzeAnalyze BPM, key, beats, segments, and optional semantic tags
Piano Audio to MIDI/task/piano_audio_to_midiConvert piano audio into a MIDI file
Piano Audio Enhancement/task/piano_audio_enhanceTranscribe and re-render piano audio into an enhanced WAV file
Voice Clone TTS/task/audio_tts_cloneProvide text and an artist to synthesize speech in that artist's voice

Supported File Formats

Audio processing APIs support: mp3, wav, m4a, aac, flac, ogg, and video files with audio tracks (mp4, mov, etc.).

Next Steps