Livekit manager api #2259
Open
Livekit manager api #2259
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
threshold_low (default 0.2) → below this is definitely silence. min_silence_duration_ms → how long silence must last before we declare end of speech, frame_window_threshold → minimum number of 'True' frames in recent window to count as speaking.
New Pull Request to Stable2 Branch after translating the web app from Chinese to English
tranlated to english server and mqtt folders
all-functions-converted-to-indian-calender-weather-location-date-time…
…roperly - Fixed timing issue where had_speaking_state was reset before ASR decision - Removed echo suppression to capture full audio - Added proper speech confidence tracking (SPEAKING vs STARTING states) - Audio now records on voice detection but only processes if speech detected - Added debug logging for troubleshooting VAD state transitions 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
User agents are displaying in admin panel
Timezone in chathistory
Vad cliping initail audio fixed
- Added LiveKit server with proper folder structure - Integrated MQTT gateway for ESP32 communication - Added agent with STT/TTS capabilities - Sanitized .env.example with placeholder API keys - Updated project configuration files 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
devLivekit structured
- Add comprehensive LiveKit agent configuration - Support for both manager-api and local configuration modes - Include LLM, STT, TTS, VAD, and memory configurations - Use placeholder values for API keys for security - Configure LiveKit server connection settings
- Add Groq-based LLM models for LiveKit agents - Add Groq TTS models with different voices - Add Groq ASR models for speech recognition - Add LiveKit-optimized VAD models - Add memory models (simple and Mem0AI) - Add intent recognition models - Add LiveKit agent templates (English and Chinese) - All API keys use placeholder values for security
- Exclude the RAG agent directory from version control - Prevents accidental inclusion of external dependencies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.