Skip to content

Commit 4c073f8

Browse files
committed
fix(orb): Use correct Gemini model with transcription support
VTID-01225: Update model from 'gemini-live-2.5-flash-native-audio' to 'gemini-2.5-flash-native-audio-preview-12-2025' which is documented as supporting input_audio_transcription and output_audio_transcription. Research findings: - The old model name format didn't match documented working examples - Preview model with date suffix has confirmed transcription support - Config placement at setup level (not in generation_config) is correct Sources: - googleapis/python-genai#1279 - googleapis/js-genai#1212 - Vertex AI Live API documentation https://claude.ai/code/session_01FGZx1ZrwRtx5JN6m4rRMqh
1 parent 154394a commit 4c073f8

1 file changed

Lines changed: 2 additions & 1 deletion

File tree

‎services/gateway/src/routes/orb-live.ts‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -490,7 +490,8 @@ const liveSessions = new Map<string, GeminiLiveSession>();
490490
// VTID-01155: Vertex AI Live API configuration
491491
const VERTEX_PROJECT_ID = process.env.GOOGLE_CLOUD_PROJECT || process.env.GCP_PROJECT_ID || '';
492492
const VERTEX_LOCATION = process.env.VERTEX_AI_LOCATION || 'us-central1';
493-
const VERTEX_LIVE_MODEL = 'gemini-live-2.5-flash-native-audio'; // Live API model for BidiGenerateContent
493+
// VTID-01225: Use preview model that supports input/output audio transcription
494+
const VERTEX_LIVE_MODEL = 'gemini-2.5-flash-native-audio-preview-12-2025'; // Live API model for BidiGenerateContent
494495
const VERTEX_TTS_MODEL = 'gemini-2.5-flash-tts'; // Cloud TTS with Gemini voices
495496

496497
// VTID-01155: Google Cloud Text-to-Speech client with Gemini voices

0 commit comments

Comments
 (0)