3 Commits

Author	SHA1	Message	Date
Xin Wang	9e2374f492	Add voice state tags, SuperTTS configs, and demo WS log groups. ... Parse leading <state> tags from LLM replies and emit response.state over the product websocket while stripping tags from TTS/text streams. Add FastGPT+Xfyun voice configs (including state-enabled preset), SuperTTS support, and context sync for interrupted turns. Refresh the voice demo with a state indicator and collapsible audio delta websocket log groups. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-28 11:32:20 +08:00
Xin Wang	b14ef64665	Add configuration files for FastGPT and Xfyun voice services, enhancing LLM service capabilities. Update LLMConfig to include chat_id, variables, detail, and timeout settings. Refactor create_llm_service to support FastGPT integration and adjust pipeline to handle chat_id and greeting prompts. Implement context synchronization for interrupted assistant turns in text streaming.	2026-05-26 10:56:38 +08:00
Xin Wang	bc2aa5b133	Integrate product-ws voice demo on port 8000 alongside REST API. ... Add src/voice Pipecat pipeline, browser demo at /voice-demo, and config/voice.json. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-22 16:26:06 +08:00