Gemini Live API not returning outputAudioTranscription event

Gemini API
, ,
1

Hi there,

I’m using Gemini Live API (gemini-2.5-flash-native-audio-preview-12-2025) in NodeJS and I receive audio responses fine via the modelTurn event. However, I am not getting the outputAudioTranscription event.

Here is the code to my init function.

const initSession = async () => {
        const gemini = new GoogleGenAI({apiKey: process.env.GEMINI_API_KEY});
        const model = 'gemini-2.5-flash-native-audio-preview-12-2025';
        const config = {
            responseModalities: [Modality.AUDIO],
            outputAudioTranscription: {}
        };

        try {
            let startSession = await gemini.live.connect({
                model,
                config,
                callbacks: {
                    onopen: () => console.log('Connected to Gemini Live API'),
                    onmessage: (message) => {
                        if ('serverContent' in message) {
                            console.log(message)

                            if ('modelTurn' in message.serverContent) {
                                const response = message.serverContent.modelTurn.parts[0];
                                if (response) {
                                    if ('inlineData' in response) {
                                        const {data, mimeType} = response.inlineData;
                                        setResponseAudioString(prev => prev + data);
                                        setResponseMimeType(mimeType);
                                    }
                                }
                            }
                            else if ('outputTranscription' in message.serverContent) {
                                console.log("OUTPUT TRANSCRIPTION", message.serverContent.outputTranscription);
                                setResponseLog(prevResponses => [...prevResponses, message.serverContent.outputTranscription.text]);
                            }
                            else if ('generationComplete' in message.serverContent) {
                                const el = document.getElementById("chat-window");
                                if (el) el.scrollTop = el.scrollHeight;
                                setAudioReady(true);
                            }
                        }
                    },
                    onerror: (e) => {
                        console.error('Error', e.message);
                    },
                    onclose: (e) => {
                        console.error('Close:' + e.reason);
                    },
                },
                config: {
                    responseModalities: [Modality.AUDIO],
                    systemInstruction: "You are a helpful and friendly AI assistant.",
                    speechConfig: {
                        voiceConfig: {prebuiltVoiceConfig: {voiceName: 'Orus'}},
                    },
                },
            });
            setSession(()=>startSession);
            setLoading(false);
        } catch (e) {
           console.error(e);
        }
    };

Any help would be appreciated!

2

Hi, I resolved the issue. Turns out I was passing a 2nd config object with Transcription not enabled.