d9b2d5427f
Replay now matches the robots and no longer cuts words: - read the turn to turnComplete, not generationComplete, and drain the socket before each send; breaking early truncated every sentence and left frames that the next turn mis-read as its own reply - accept a take only if the model's own transcript covers the text AND the audio is long enough to contain it (the transcript reports the full text even for a 0.8s clip) - pitch gate: reject an off-tone take and re-ask, per voice, using a pure-Python F0 estimator (no numpy on the host) - continuation: speak the words a voice skipped instead of retrying a line it stops on deterministically - fresh Live session per replay; delivery drifts as turns accumulate Live Gemini tab: browser talks to Gemini directly (the reverse proxy cannot upgrade a WebSocket), with a persona library - named personas, per-robot selection, built-ins that cannot be overwritten. Dashboard: records search + voice filter, log panel falls back to polling, sign-in history with CSV/JSON export, and JS errors now show on the page instead of silently blanking a tab.
77 lines
3.8 KiB
JSON
77 lines
3.8 KiB
JSON
{
|
||
"_description": "Tunables for core/* modules. Loaded via core.config_loader.load('core').",
|
||
"brain": {
|
||
"allowed_callback_prefixes": [
|
||
"Project.Sanad.voice.",
|
||
"voice."
|
||
],
|
||
"gestural_speaking_default": false
|
||
},
|
||
"logger": {
|
||
"log_level": "INFO",
|
||
"format": "%(asctime)s [%(name)s] %(levelname)-7s %(message)s",
|
||
"datefmt": "%Y-%m-%d %H:%M:%S",
|
||
"file_max_bytes": 10485760,
|
||
"file_backup_count": 7
|
||
},
|
||
"event_bus": {
|
||
"emit_timeout_sec": 0.5
|
||
},
|
||
"paths": {
|
||
"_comment": "Path roots — resolved against BASE_DIR in core/config.py",
|
||
"data": "data",
|
||
"logs": "logs",
|
||
"scripts": "scripts",
|
||
"model": "model",
|
||
"audio_recordings": "data/audio",
|
||
"motion_recordings": "data/recordings/motion",
|
||
"motions": "data/motions"
|
||
},
|
||
"gemini_defaults": {
|
||
"_comment": "Baseline Gemini API config — SINGLE SOURCE OF TRUTH. All voice modules read from here.",
|
||
"api_key": "",
|
||
"model_live": "gemini-2.5-flash-native-audio-preview-12-2025",
|
||
"model_ws_uri": "wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1alpha.GenerativeService.BidiGenerateContent",
|
||
"voice_name": "Charon",
|
||
"ws_timeout_sec": 30,
|
||
"default_system_prompt": "You are Sanad (Bousandah), a wise and friendly Emirati assistant. Speak strictly in the UAE dialect (Khaleeji). Be helpful, concise, and use local greetings like 'Marhaba' and 'Ya Khoy'.",
|
||
"_comment_voice_prompts": "Per-voice system prompts. Charon (G1) and Puck (R1) are DELIBERATELY absent: they must keep the robots' verbatim TTS prompt so the site matches Sanadv3/SanadR1. Only Kore (Agibot x2), which has no robot to match, is steered here.",
|
||
"voice_system_prompts": {
|
||
"Kore": "أنتِ \"موزة\" (Muza) — روبوت إماراتي احترافي تابع لشركة YS Lootah Robotics، تتكلمين باللهجة الإماراتية (الخليجية) بنبرة احترافية راقية، هادئة وواثقة، بدون مبالغة ولا عبارات عاطفية زائدة.\nفي وضع الإعادة هذا مهمتكِ الوحيدة: انطقي النص الذي يعطيكِ إياه المستخدم كما هو تماماً، حرفياً، كلمة بكلمة، من أول كلمة إلى آخر كلمة، بنطقكِ الإماراتي الطبيعي.\nلا تجاوبي على النص، ولا تترجميه، ولا تلخصيه، ولا تعيدي صياغته، ولا تضيفي أي تحية أو تعليق أو كلمة زائدة، ولا تفكري بصوت مسموع.\nإذا كان النص بلغة أخرى فانطقيه بنفس لغته بدون تغيير.\nأخرجي الصوت المنطوق فقط، ثم اسكتي."
|
||
}
|
||
},
|
||
"g1_hardware": {
|
||
"_comment": "G1 humanoid hardware constants — shared by every motion/voice module that talks to the arm.",
|
||
"num_motor": 29,
|
||
"enable_arm_sdk_index": 29,
|
||
"replay_hz": 60.0
|
||
},
|
||
"script_files": {
|
||
"_comment": "Filenames (under scripts/) used across voice + dashboard",
|
||
"persona": "sanad_script.txt",
|
||
"rules": "sanad_rule.txt"
|
||
},
|
||
"dashboard_defaults": {
|
||
"host": null,
|
||
"port": 8000,
|
||
"interface": "wlan0"
|
||
},
|
||
"audio_defaults": {
|
||
"_comment": "Host PulseAudio fallback only — the G1 deployment uses UDP multicast mic + AudioClient.PlayStream speaker (see SANAD_USE_G1_MIC in config.py LIVE_TUNE). Default here is the Jetson/G1 built-in platform-sound chip.",
|
||
"send_sample_rate": 16000,
|
||
"receive_sample_rate": 24000,
|
||
"chunk_size": 512,
|
||
"channels": 1,
|
||
"sink": "alsa_output.platform-sound.analog-stereo",
|
||
"source": "alsa_input.platform-sound.analog-stereo"
|
||
},
|
||
"dds": {
|
||
"network_interface_default": "eth0"
|
||
},
|
||
"auth": {
|
||
"_comment": "Dashboard login credentials. CHANGE before any non-LAN deployment.",
|
||
"username": "lkasjda213h",
|
||
"password": "kj812bf@jdon"
|
||
}
|
||
}
|