Xin WangandCursor 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

config

Add voice state tags, SuperTTS configs, and demo WS log groups.

2026-05-28 11:32:20 +08:00

docs

提示词添加车辆预先提取和手机号多次拼接输入

2026-02-03 17:33:45 +08:00

examples

提示词添加车辆预先提取和手机号多次拼接输入

2026-02-03 17:33:45 +08:00

src

Add voice state tags, SuperTTS configs, and demo WS log groups.

2026-05-28 11:32:20 +08:00

static/voice-demo

Add voice state tags, SuperTTS configs, and demo WS log groups.

2026-05-28 11:32:20 +08:00

test/api

Add stream text output

2026-02-02 17:54:55 +08:00

workflow

提示词添加车辆预先提取和手机号多次拼接输入

2026-02-03 17:33:45 +08:00

.env

update default env

2026-05-22 16:41:24 +08:00

.gitignore

use fastgpt python sdk

2026-01-08 16:22:25 +08:00

entrypoint.sh

Add env and entrypoint

2025-06-20 10:03:39 +08:00

pytest.ini

Add api server code and workflow

2025-04-29 15:03:02 +08:00

requirements.txt

Integrate product-ws voice demo on port 8000 alongside REST API.

2026-05-22 16:26:06 +08:00

S

Description

No description provided

12 MiB

Languages

Python 69.5%

JavaScript 18%

CSS 8.4%

HTML 4.1%