feat: Add selectable OpenAI Realtime API model in voice chat settings #296
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
- Add model parameter to route.ts to accept selected models - Update voice chat state to store both voice and model in providerOptions - Add dedicated model selector UI in voice chat settings - Support gpt-4o-realtime-preview, gpt-realtime, and gpt-realtime-mini models - Rename voice selector from 'Open AI' to 'Voice' for clarity
|
@mxcoppell is attempting to deploy a commit to the cgoinglove's projects 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
1 participant
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Outdated suggestions cannot be applied.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.
Summary
This PR adds the ability for users to select different OpenAI Realtime API models directly from the voice chat settings UI, replacing the previously hard-coded
gpt-4o-realtime-previewmodel.Motivation
Users were unable to configure which OpenAI Realtime model to use for voice conversations. The model was hard-coded, preventing users from trying newer models like
gpt-realtimeorgpt-realtime-miniwhich may offer better performance or cost benefits.Changes Made
route.ts): Modified to accept and use themodelparameter from request body instead of hard-coded valuestore/index.ts): Updated voice chat state to properly store bothvoiceandmodelinproviderOptionschat-bot-voice.tsx): Added new "Model" selector dropdown in voice chat settings with three options:gpt-4o-realtime-preview) - defaultgpt-realtime)gpt-realtime-mini)Features
✅ Model selection persists across sessions
✅ Independent from text chat model selection
✅ Visual indicator (checkmark) shows currently selected model
✅ Smooth settings UI with brain icon for model selector
✅ Fallback to default model if none specified
Testing
Files Changed
src/app/api/chat/openai-realtime/route.tssrc/app/store/index.tssrc/components/chat-bot-voice.tsxBreaking Changes
None - this is a backward compatible enhancement with sensible defaults.