mirror of
https://github.com/justLV/onju-v2
synced 2026-04-21 23:57:26 +00:00
19d48d4e3c
- Add managed conversation backend for OpenClaw (x-openclaw-message-channel header, user field for device identity) - Replace aggressive interrupt logic with VAD-aware check: only interrupt on actual speech, not background noise/trailing packets - Fix 0xDD timeout units (was milliseconds, now seconds) and keep callActive alive with 30s hold during LLM+TTS processing - Set callActive on boot for VOX mode so device accepts audio without tap - Mic timeout no longer kills callActive — only double-tap ends the call - LED feedback: scale to configured led_power, let device handle fade-down - Add greeting toggle, TTS/SEND logging, pyserial dep, setuptools config
69 lines
2.2 KiB
Text
69 lines
2.2 KiB
Text
asr:
|
|
url: "http://localhost:8100" # parakeet-asr-server
|
|
|
|
conversation:
|
|
backend: "local" # "local" or "managed" (e.g. OpenClaw)
|
|
|
|
local:
|
|
base_url: "http://localhost:8080/v1" # mlx_lm.server, Ollama, OpenRouter, Gemini, etc.
|
|
api_key: "none" # set key or use ${ENV_VAR} reference
|
|
model: "mlx-community/gemma-3-4b-it-qat-4bit"
|
|
max_messages: 20
|
|
max_tokens: 300
|
|
system_prompt: "You are a helpful voice assistant. Keep responses concise (under 2 sentences)."
|
|
persist_dir: "data/conversations" # per-device message history (omit to disable)
|
|
# Gemini example:
|
|
# base_url: "https://generativelanguage.googleapis.com/v1beta/openai/"
|
|
# api_key: "${GEMINI_API_KEY}"
|
|
# model: "gemini-3.1-flash-lite-preview"
|
|
|
|
managed:
|
|
base_url: "http://127.0.0.1:18789/v1" # OpenClaw gateway
|
|
api_key: "${OPENCLAW_GATEWAY_TOKEN}" # env var reference
|
|
model: "openclaw/default"
|
|
max_tokens: 300
|
|
message_channel: "onju-voice" # x-openclaw-message-channel header
|
|
# provider_model: "anthropic/claude-opus-4-6" # optional: override backend LLM
|
|
|
|
tts:
|
|
backend: "elevenlabs" # "qwen3" (local) or "elevenlabs" (cloud)
|
|
default_voice: "Rachel"
|
|
qwen3:
|
|
url: "http://localhost:8880"
|
|
model: "mlx-community/Qwen3-TTS-12Hz-1.7B-Base-4bit"
|
|
ref_audio: ""
|
|
ref_text: ""
|
|
elevenlabs:
|
|
api_key: "" # your ElevenLabs API key
|
|
default_voice: "Rachel"
|
|
voices:
|
|
Rachel: "21m00Tcm4TlvDq8ikWAM" # add your voice IDs here
|
|
|
|
vad:
|
|
threshold: 0.5 # speech onset probability
|
|
neg_threshold: 0.35 # speech offset probability (hysteresis)
|
|
silence_time: 1.5
|
|
pre_buffer_s: 1.0
|
|
|
|
network:
|
|
udp_port: 3000
|
|
tcp_port: 3001
|
|
multicast_group: "239.0.0.1"
|
|
multicast_port: 12345
|
|
control_port: 3002
|
|
|
|
audio:
|
|
sample_rate: 16000
|
|
chunk_size: 480 # 30ms at 16kHz
|
|
opus_frame_size: 320 # 20ms at 16kHz
|
|
|
|
device:
|
|
default_volume: 8
|
|
default_mic_timeout: 60
|
|
led_fade: 6
|
|
led_power: 35
|
|
led_update_period: 0.2
|
|
greeting_wav: "data/hello_imhere.wav"
|
|
|
|
logging:
|
|
level: "INFO"
|