Xin Wang 6df6c16e1d Implement UserStartedSpeakingFrame handling in voice pipeline ...

- Added support for UserStartedSpeakingFrame to enhance user interaction tracking.
- Updated the pipeline to reset idle prompt count when a user starts speaking, improving responsiveness during conversations.
- Integrated new event handlers for better management of user turn events and upstream frame processing.

2026-05-29 16:51:51 +08:00

config

Enhance voice configuration with idle prompt features and new TTS settings

2026-05-29 16:27:05 +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

Implement UserStartedSpeakingFrame handling in voice pipeline

2026-05-29 16:51:51 +08:00

static/voice-demo

Add camera functionality to voice demo with UI updates and state management

2026-05-28 15:13:54 +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 VOICE_CONFIG to use new FastGPT state-enabled configuration and add TEXT_DELTA log group for websocket responses.

2026-05-28 13:46:33 +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

Description

No description provided

12 MiB

Languages

Python 66.3%

JavaScript 19.9%

CSS 9.3%

HTML 4.5%