aria-tts / engine.py

Commit History

2 days ago

  1. Accept vq_codes references so a context token skips the codec

    VoiceClimax
    d96f284
  2. Add /speech: chunked take with a context token, and emit the sampled codes

    VoiceClimax
    a0646ab
  3. Streaming speech service on ZeroGPU

    VoiceClimax
    b1c28a5