Gemini Live API - Transcription finished flag never updates in Javascript SDK

[fidalgok]

Environment details

• Programming language: TypeScript / JavaScript
• OS: macOS 15.x (Sequoia)
• Language runtime version: Node.js 22.16.0
• Package version: @google/genai 1.44.0

---

Steps to reproduce

Model: gemini-2.5-flash-native-audio-preview-12-2025
API: Live API (WebSocket, v1alpha), ephemeral token auth

1. Connect to the Live API with both inputAudioTranscription: {} and outputAudioTranscription: {} enabled in the session config:

   const session = await ai.live.connect({
     model: "gemini-2.5-flash-native-audio-preview-12-2025",
     config: {
       responseModalities: [Modality.AUDIO],
       inputAudioTranscription: {},
       outputAudioTranscription: {},
     },
     callbacks: {
       onmessage: (message: LiveServerMessage) => {
         console.log(message.serverContent?.inputTranscription);
         console.log(message.serverContent?.outputTranscription);
       }
     }
   });

2. Speak several complete sentences, then wait for the model to respond with a complete turn.
3. Observe the inputTranscription and outputTranscription objects logged from serverContent.

---

Expected behavior

Per the SDK's TypeScript types, and the documented pattern for streaming transcription, the final transcription message for each speaker turn should include finished: true, signaling that the turn is complete and the accumulated text can be finalized.

This is the natural mechanism for knowing when to flush a transcript buffer.

Referenced SDK Patterns

• Live Server Content Interface
• Audio Transcription Interface

---

Actual behavior

The finished field is never present on either inputTranscription or outputTranscription messages across an entire conversation.

Each transcription message contains only a text field with a fragment. There is no per-transcription signal indicating that a turn has ended.

The only reliable turn-boundary signal is message.serverContent?.turnComplete === true, which arrives on a separate message with no transcription payload. It also fires only at the end of the model's turn, not the user's.

---

Workaround in use

• Accumulate inputTranscription.text fragments into a buffer.
• Flush the user buffer when the first outputTranscription.text fragment arrives, treating that as an implicit signal that the user has finished speaking.
• Flush the model buffer when turnComplete: true fires.

This works, but it requires developers to reverse-engineer the signal sequence instead of relying on the documented finished flag.

[Varun-S10]

Hi @fidalgok, Thank you for reporting this issue. To help us investigate, could you please let us know whether you are using a Gemini API key or Vertex AI? Also, could you confirm if you are still experiencing this problem on the latest version of @google/genai?

[fidalgok]

Hi @Varun-S10 , This is with a Gemini API key. I can also confirm after updating from @google/genai@1.44.0 → @google/genai@1.46.0 the issue persists. I've added a code block and a screenshot below for further information. This is an abbreviated section of the hook I'm using to instantiate the client.

onmessage: (message: LiveServerMessage) => {
            if (!isActive()) return;

            const sc = message.serverContent;
            // temp debug
            console.log("Live API message:", {
              turnComplete: sc?.turnComplete,
              inputFinished: sc?.inputTranscription?.finished,
              outputFinished: sc?.outputTranscription?.finished,
              interrupted: sc?.interrupted,
              generationComplete: sc?.generationComplete,
            });

[Varun-S10]

Hi @fidalgok, Thank you for bringing this to our attention. We have reproduced the issue. We truly appreciate you flagging this issue, we will file a bug internally.