mirror of
https://github.com/siteboon/claudecodeui.git
synced 2026-06-26 13:35:49 +08:00
Adds a push-to-talk mic button in the composer and a read-aloud button on assistant messages. Both are opt-in and hidden unless a voice backend is configured via VOICE_SIDECAR_URL. The auth-gated /api/voice proxy forwards to a configurable backend exposing /transcribe and /tts (provider-agnostic); the frontend probes /api/voice/health and hides the controls when disabled. Adds i18n keys and docs/voice.md. Includes a local, no-API-key reference backend in voice-sidecar/ (faster-whisper for STT, Kokoro-82M for TTS, both CPU-capable).
15 lines
545 B
Plaintext
15 lines
545 B
Plaintext
# Voice sidecar config (all optional — these are the defaults).
|
|
# The sidecar binds 127.0.0.1 only; CloudCLI's Express proxy reaches it.
|
|
|
|
# Port the sidecar listens on (CloudCLI reaches it via VOICE_SIDECAR_URL).
|
|
VOICE_PORT=8765
|
|
|
|
# faster-whisper model size: tiny | base | small | medium | large-v3
|
|
WHISPER_MODEL_SIZE=base
|
|
# cpu (int8, default) or cuda (float16, needs a CUDA torch in the venv)
|
|
WHISPER_DEVICE=cpu
|
|
|
|
# Kokoro voice (see https://github.com/hexgrad/kokoro for the full list) and language code.
|
|
KOKORO_VOICE=af_heart
|
|
KOKORO_LANG=a
|