Files

• compose.cuda-cdi.yaml (yaml)
• compose.cuda.yaml (yaml)
• pyproject.toml (toml)
• pyannote_speaker_segmentation.py (python)
• silero_vad_v5.py (python)
• CLAUDE.md (markdown)
• README.md (markdown)
• Taskfile.yaml (yaml)
• compose.cpu.yaml (yaml)
• compose.observability.yaml (yaml)
• compose.yaml (yaml)
• configuration ()
• grafana ()
• datasources.yaml (yaml)
• loki.yaml (yaml)
• opentelemetry-collector.yaml (yaml)
• prometheus.yaml (yaml)
• tempo.yaml (yaml)
• docs ()
• api.md (markdown)
• configuration.md (markdown)
• index.md (markdown)
• installation.md (markdown)
• openapi.json (json)
• troubleshooting.md (markdown)
• usage ()
• dynamic-loading.md (markdown)
• model-discovery.md (markdown)
• open-webui-integration.md (markdown)
• realtime-api.md (markdown)
• speech-embedding.md (markdown)
• LICENSE (plaintext)
• speech-to-text.md (markdown)
• text-to-speech.md (markdown)
• vad.md (markdown)
• voice-chat.md (markdown)
• examples ()
• javascript ()
• index.js (javascript)
• youtube ()
• script.sh (bash)
• mkdocs.yml (yaml)
• model_aliases.json (json)
• packages ()
• speaches-cli ()
• pyproject.toml (toml)
• pyrightconfig.json (json)
• ruff.toml (toml)
• scripts ()
• create_kokoro_v1_onnx_model_repos.py (python)
• create_piper_model_repos.py (python)
• performance_benchmark.py (python)
• realtime_transcription_client.py (python)
• src ()
• speaches ()
• api_types.py (python)
• audio.py (python)
• config.py (python)
• dependencies.py (python)
• diarization.py (python)
• executors ()
• kokoro.py (python)
• parakeet.py (python)
• piper.py (python)
• ATTRIBUTION.md (markdown)