Input and Output Transcription Always Returning "Finished" as Null

[Ali-Olliek]

Thanks for stopping by to let us know something could be better!

PLEASE READ: If you have a support contract with Google, please create an issue in the support console instead of filing on GitHub. This will ensure a timely response.

Is this a client library issue or a product issue? We will only be able to assist with issues that pertain to the behaviors of this library. If the issue you're experiencing is due to the behavior of the product itself, please visit the Support page to reach the most relevant engineers.

If the support paths suggested above still do not result in a resolution, please provide the following details.

Environment details

• Programming language: Python
• OS: Windows
• Language runtime version: 3.10.0
• Package version: 1.3.0

Steps to reproduce

1. Talk to Gemini Live.
2. Print the data coming from the event server_content.output_transcription and server_content.input_transcription
3. The transcription object has the following structure:

class Transcription(_common.BaseModel):
  """Audio transcription in Server Conent."""

  text: Optional[str] = Field(
      default=None,
      description="""Transcription text.
      """,
  )
  finished: Optional[bool] = Field(
      default=None,
      description="""The bool indicates the end of the transcription.
      """,
  )

4. We should expect the finished to be true when the transcription is finished generation (On last chunk), however it is always returning None.

---

I want basically to notify the client when the input/output transcription is done which is why this flag would be helpful.

Thanks!