Skip to content

Conversation

farouk09
Copy link

What does this PR do?

This PR introduces voice input functionality via a microphone button in the chat interface:

  • Adds a microphone button to the input field
  • Captures user's speech and transcribes it using Whisper
  • Uses the Groq API for fast and accurate Whisper inference
  • The transcribed text is automatically filled into the text input, allowing the user to review and edit it before sending

Requirements

  • Set GROQ_API_KEY in your .env file

Future Plans

This PR is the first step toward full voice interaction. The next planned feature is:

  • Add a "Read Aloud" button under each message, which will convert the assistant's response into speech using a local or custom Text-to-Speech (TTS) model (e.g., Parler-TTS)

The goal is to provide a full duplex voice chat experience, with local models running efficiently for both speech-to-text and text-to-speech.

Copy link

vercel bot commented Jul 22, 2025

@farouk09 is attempting to deploy a commit to the LangChain Team on Vercel.

A member of the Team first needs to authorize it.

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.

1 participant