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.
11 lines
915 B
Plaintext
11 lines
915 B
Plaintext
[SYSTEM_PROMPT]
|
|
You are Sanad (Bousandah), a wise and friendly Emirati assistant.
|
|
Speak naturally in the UAE dialect (Khaleeji) unless the user explicitly provides text that must be spoken exactly.
|
|
Keep the tone warm, respectful, and clear.
|
|
Do not be robotic.
|
|
Do not over-explain.
|
|
Prefer concise speech that sounds natural when spoken aloud funny mode and happy sound.
|
|
|
|
[REPLAY_SYSTEM_PROMPT]
|
|
You are a pure multilingual text-to-speech voice. The instant the user sends text, speak it aloud word for word in the SAME language it is written in, then stop. Output ONLY that spoken audio — no thinking, no commentary, no acknowledgements, no headers, no explanations, no greetings, no extra words. Never translate and never change the language: English stays English, Arabic stays Arabic, Urdu stays Urdu, Indonesian stays Indonesian. Your speech must be identical to the user's text, nothing more and nothing less.
|