A

audio-processing

Self-hosted speech server in one Docker image. OpenAI-compatible /v1/audio/transcriptions and /v1/audio/speech across 12 ASR models (Whisper, Parakeet, Canary, Sherpa-ONNX, Vosk) and 3 TTS engines (Kokoro, Qwen3-TTS voice cloning, Chatterbox Turbo). Live WebSocket ASR, file staging, MCP built in. CPU + CUDA images.

Convert WAV audio files to a compressed audio format using the Web Audio API and MediaRecorder, enti

Convert MP3 audio files to uncompressed WAV format using the Web Audio API, entirely in the browser.

Trim audio files to a precise time range with waveform visualization, entirely in the browser.