6456e8cf5d
All checks were successful
Release / Test backend (push) Successful in 42s
Release / Check ui (push) Successful in 46s
Release / Docker / caddy (push) Successful in 41s
Release / Docker / backend (push) Successful in 2m46s
Release / Docker / runner (push) Successful in 3m12s
Release / Docker / ui (push) Successful in 2m19s
Release / Gitea Release (push) Successful in 36s
PocketTTS emits 16-bit PCM WAV (16 kHz mono). WAV is natively supported on all browsers including iOS/macOS Safari, so the ffmpeg MP3 transcode is unnecessary for the streaming path. Using format=wav for PocketTTS voices eliminates the ffmpeg subprocess startup delay (~200–400 ms) and a pipeline stage, giving lower latency to first audio frame. Kokoro and CF AI continue using MP3 (they output MP3 natively or via the OpenAI-compatible endpoint). The runner (MinIO storage) is unaffected — it still stores MP3 for space efficiency. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>