Skip to content

Gemini Realtime Model Transcriptions not working #8

@ArunkumarKv-iN

Description

@ArunkumarKv-iN

I am trying to enable Transcriptions for gemini realtime model but im not receiving any transcriptions.
below is how im creating my model
model = google.realtime.RealtimeModel(
instructions=(
"You are a conversational AI designed to function as a voice assistant. "
),
modalities=cast(list[Modality], config.modalities),
voice=config.voice,
temperature=config.temperature,
max_output_tokens=int(config.max_response_output_tokens),
api_key=os.getenv("GEMINI_API_KEY"),
enable_agent_audio_transcription=True,
enable_user_audio_transcription=True,

)

I have also tried using transcriptionsOptions
transcription_options = AgentTranscriptionOptions(user_transcription=True, agent_transcription=True)
agent = MultimodalAgent(model=model, chat_ctx=chat_ctx, fnc_ctx=fnc_ctx, transcription=transcription_options)

Still didnt receive any transcriptions in events.

Please help on this issue.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions