Skip to content

feat(voice): implement voice mode, audio transcription endpoint, and … - #2

Open
CodewithJha wants to merge 2 commits into
LucknowAI:devfrom
CodewithJha:priyanshu/voice-feature
Open

feat(voice): implement voice mode, audio transcription endpoint, and …#2
CodewithJha wants to merge 2 commits into
LucknowAI:devfrom
CodewithJha:priyanshu/voice-feature

Conversation

@CodewithJha

Copy link
Copy Markdown

…rate limit retries

Priyanshu Jha and others added 2 commits July 24, 2026 18:47
Resolve conflicts keeping voice mode, Groq transcription, and rate-limit
retries; use gemini-3-flash-preview default and events naming from dev.

Co-authored-by: Cursor <cursoragent@cursor.com>
@ASahu16
ASahu16 requested review from ASahu16 and naruto-91 August 10, 2026 13:19

@ASahu16 ASahu16 left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

  • Audio input isn’t being captured correctly. It sometimes automatically detects “Thanks for watching” as the user’s input and sends a response to it.
  • On the first audio message, the conversation page doesn’t display the conversation/chat bubble properly.
  • The conversation UI only starts appearing correctly after sending the second message.

Comment thread src/api/voice.py

router = APIRouter(prefix="/voice", tags=["Voice"])

GROQ_TRANSCRIPTION_URL = "https://api.groq.com/openai/v1/audio/transcriptions"

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Move this url to configuration.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants