-
feat: graph-decoded streaming, prebuffer_ms and cancel-on-disconnect (v6.13)
released this
2026-10-04 00:11:12 +02:00 | 11 commits to main since this release- Fixed-window CUDA-graph codec decode for streaming (TTS_GRAPH_DECODE=0 disables)
- Per-request chunk_size (2-24) on /v1/audio/speech
- prebuffer_ms (0-10000) to hold back audio before sending
- Stop generation on client disconnect
- Recommend --max-seq-len 2048 for the streaming container
Co-Authored-By: Claude Sonnet 5.5 noreply@anthropic.com
Downloads