124 lines
3.6 KiB
JSON
124 lines
3.6 KiB
JSON
{
|
|
"_description": "Tunables for voice/* modules. Loaded via core.config_loader.load('voice').",
|
|
|
|
"sanad_voice": {
|
|
"_comment": "voice/sanad_voice.py — main live voice subprocess. Gemini API credentials (api_key, model, voice_name) come from core_config.json's gemini_defaults — single source of truth.",
|
|
"mic_gain": 1.0,
|
|
"play_chunk_bytes": 96000,
|
|
"log_dir": "~/logs",
|
|
"log_name": "gemini_live_v2",
|
|
"session_timeout_sec": 660,
|
|
"max_reconnect_delay_sec": 30,
|
|
"max_consecutive_errors": 10,
|
|
"no_messages_timeout_sec": 30
|
|
},
|
|
|
|
"mic_udp": {
|
|
"_comment": "G1 built-in mic — UDP multicast subscriber",
|
|
"group": "239.168.123.161",
|
|
"port": 5555,
|
|
"buffer_max_bytes": 64000,
|
|
"read_timeout_sec": 0.04,
|
|
"socket_timeout_sec": 1.0
|
|
},
|
|
|
|
"speaker": {
|
|
"_comment": "G1 built-in speaker — AudioClient.PlayStream wrapper",
|
|
"app_name": "sanad",
|
|
"begin_stream_pause_sec": 0.15,
|
|
"wait_finish_margin_sec": 0.3
|
|
},
|
|
|
|
"vad": {
|
|
"_comment": "Gemini Live server-side voice-activity-detection config",
|
|
"start_sensitivity": "START_SENSITIVITY_HIGH",
|
|
"end_sensitivity": "END_SENSITIVITY_LOW",
|
|
"prefix_padding_ms": 20,
|
|
"silence_duration_ms": 200
|
|
},
|
|
|
|
"barge_in": {
|
|
"threshold": 500,
|
|
"loud_chunks_needed": 3,
|
|
"cooldown_sec": 0.3,
|
|
"echo_suppress_below": 500,
|
|
"ai_speak_grace_sec": 0.15
|
|
},
|
|
|
|
"recording": {
|
|
"enabled": true,
|
|
"dir_relative": "data/recordings"
|
|
},
|
|
|
|
"system_prompt": {
|
|
"_comment": "Persona filename lives in core.script_files.persona; default text in core.gemini_defaults.default_system_prompt. This section is now metadata-only."
|
|
},
|
|
|
|
"typed_replay": {
|
|
"_comment": "voice/typed_replay.py — max_text_len comes from dashboard.api_input",
|
|
"monitor_chunk_size": 512,
|
|
"monitor_tail_sec": 0.2
|
|
},
|
|
|
|
"live_gemini_subprocess": {
|
|
"_comment": "voice/live_gemini_subprocess.py — LiveGeminiSubprocess",
|
|
"log_tail_size": 2000,
|
|
"transcript_tail_size": 30,
|
|
"log_name": "live_gemini_subprocess",
|
|
"stop_timeout_sec": 3.0,
|
|
"terminate_timeout_sec": 2.0,
|
|
"noisy_prefixes": [
|
|
"ALSA lib ",
|
|
"Expression 'alsa_",
|
|
"Cannot connect to server socket",
|
|
"jack server is not running"
|
|
],
|
|
"noisy_fragments": [
|
|
"Unknown PCM",
|
|
"Evaluate error",
|
|
"snd_pcm_open_noupdate",
|
|
"PaAlsaStream",
|
|
"snd_config_evaluate",
|
|
"snd_func_refer"
|
|
]
|
|
},
|
|
|
|
"live_voice_loop": {
|
|
"_comment": "voice/live_voice_loop.py — arm phrase dispatcher. arm_txt filename comes from core.script_files.arm_phrases",
|
|
"trigger_log_size": 100,
|
|
"poll_interval_sec": 0.1,
|
|
"deferred_default": false
|
|
},
|
|
|
|
"local_tts": {
|
|
"_comment": "voice/local_tts.py — offline Coqui TTS",
|
|
"model_subdir": "speecht5_tts_clartts_ar",
|
|
"vocoder_subdir": "speecht5_hifigan",
|
|
"xvector_filename": "arabic_xvector_embedding.pt",
|
|
"sample_rate": 16000,
|
|
"channels": 1
|
|
},
|
|
|
|
"gemini_client": {
|
|
"_comment": "voice/gemini_client.py — default_system_prompt comes from core.gemini_defaults",
|
|
"recv_timeout_sec": 30,
|
|
"reconnect_max_attempts": 3,
|
|
"reconnect_initial_delay_sec": 1.0,
|
|
"reconnect_max_delay_sec": 10.0
|
|
},
|
|
|
|
"asr_buffer": {
|
|
"_comment": "text_utils.maybe_trigger_arm state machine defaults",
|
|
"window_sec": 2.0,
|
|
"short_token_bonus_sec": 1.0,
|
|
"join_no_space_maxlen": 2,
|
|
"max_chars": 120,
|
|
"stream_max_chars": 80,
|
|
"trigger_dedup_window_sec": 2.0,
|
|
"pending_arm_ttl_sec": 6.0,
|
|
"pending_arm_fallback_sec": 0.65,
|
|
"dup_call_window_sec": 0.25,
|
|
"dup_asr_repeat_window_sec": 0.9
|
|
}
|
|
}
|