Skip to content

Modalities not working #10

Description

@Sophon

I want the Realtime API to not only send the audio response but its text form too.

So I configure the modality:

OpenAIRealtimeSessionConfig(modalities = listOf("audio", "text")

And then I await the bot's response's transcription in this callback function, but none of the callback functions work - I tried onBotTranscript(), onBotLLMText() and onBotTTSText() - but none of those return the transcription of the response.

onUserTranscript() works properly.

Expected

  • (user voice input): Who is snow white?
  • onUserTranscript: Who is snow white?
  • (one of the bot transcription callbacks): Snow White is a classic fairy tale character known for her beauty, kindness...

Actual

  • (user voice input): Who is snow white?
  • onUserTranscript: Who is snow white?
  • (one of the bot transcription callbacks): no data

Is this a bug or am I configuring the client wrongly?

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