Skip to content

Fix Google Realtime API by adding missing modalities field to MessageGeneration #847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
toubatbrian merged 2 commits into from
Nov 18, 2025
Merged

Fix Google Realtime API by adding missing modalities field to MessageGeneration #847

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
62ca826
Update realtime_api.ts
toubatbrian Nov 18, 2025
a9909c1
Create friendly-dragons-approve.md
toubatbrian Nov 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .changeset/friendly-dragons-approve.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
'@livekit/agents-plugin-google': patch
---

Fix Google Realtime API missing modalities field on MessageGeneration. This resolves the "Text message received from Realtime API with audio modality" error introduced in version 1.0.18.
8 changes: 7 additions & 1 deletion plugins/google/src/beta/realtime/realtime_api.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1176,14 +1176,20 @@ export class RealtimeSession extends llm.RealtimeSession {
};

// Close audio stream if audio output is not supported by the model
if (!this.options.responseModalities.includes(Modality.AUDIO)) {
if (!this._realtimeModel.capabilities.audioOutput) {
this.currentGeneration.audioChannel.close();
}

// Determine modalities based on the model's audio_output capability
const modalities: ('text' | 'audio')[] = this._realtimeModel.capabilities.audioOutput
? ['audio', 'text']
: ['text'];

this.currentGeneration.messageChannel.write({
messageId: responseId,
textStream: this.currentGeneration.textChannel.stream(),
audioStream: this.currentGeneration.audioChannel.stream(),
modalities: Promise.resolve(modalities),
});

const generationEvent: llm.GenerationCreatedEvent = {
Expand Down
Loading