# cf-voice environment — copy to .env and fill in values # cf-voice itself does not auto-load .env; consumers (Linnet, Osprey, etc.) # load it via python-dotenv in their own startup. For standalone cf-voice # dev/testing, source this file manually or install python-dotenv. # ── HuggingFace ─────────────────────────────────────────────────────────────── # Required for pyannote.audio speaker diarization model download. # Get a free token at https://huggingface.co/settings/tokens # Also accept the gated model terms at: # https://huggingface.co/pyannote/speaker-diarization-3.1 # https://huggingface.co/pyannote/segmentation-3.0 HF_TOKEN= # ── Whisper STT ─────────────────────────────────────────────────────────────── # Model size: tiny | base | small | medium | large-v2 | large-v3 # Smaller = faster / less VRAM; larger = more accurate. # Recommended: small (500MB VRAM) for real-time use. CF_VOICE_WHISPER_MODEL=small # ── Compute ─────────────────────────────────────────────────────────────────── # auto (detect GPU), cuda, cpu CF_VOICE_DEVICE=auto # ── Mock mode ───────────────────────────────────────────────────────────────── # Set to 1 to use synthetic VoiceFrames — no GPU, mic, or HF token required. # Unset or 0 for real audio capture. CF_VOICE_MOCK= # ── Tone classifier ─────────────────────────────────────────────────────────── # Minimum confidence to emit a VoiceFrame (below this = frame skipped). CF_VOICE_CONFIDENCE_THRESHOLD=0.55