Version
- class mixedvoices.core.version.Version(version_id: str, project_id: str, prompt: str, metadata: Dict[str, Any] | None = None)[source]
Bases:
object- add_recording(audio_path: str, user_channel: str = 'left', is_successful: bool | None = None, blocking: bool = True, transcript: str | None = None, summary: str | None = None, metadata: Dict[str, Any] | None = None)[source]
Add a recording to the version
- Parameters:
audio_path (str) – Path to the audio file, should be a stereo recording with user and agent on separate channels
user_channel (str) – Audio channel of the user, either “left” or “right”. Defaults to “left”.
is_successful (Optional[bool]) – If the recording is successful or not Defaults to None. This will override the automatic successs classification if project has success criteria
blocking (bool) – If True, block until recording is processed, otherwise adds to queue and processes in the background. Defaults to True.
transcript (Optional[str]) – Transcript of the recording, this overrides the transcript generated during analysis. Defaults to None. This doesn’t stop the transcription, as that generates more granular transcript with timestamps.
summary (Optional[str]) – Summary of the recording, this overrides the summary generated during analysis. Defaults to None. This prevents summary from being generated during analysis.
metadata (Optional[Dict[str, Any]]) – Metadata to be associated with the recording. Defaults to None.
- get_recording(recording_id: str) Recording[source]
Get a recording by id
- Parameters:
recording_id (str) – The id of the recording
- get_step(step_id: str) Step[source]
Get a step by id
- Parameters:
step_id (str) – The id of the step
- property id: str
Get the name of the version
- property info: Dict[str, Any]
Get the info of the version as a dictionary
- property metadata: Dict[str, Any] | None
Get the metadata of the version
- property project_id: str
Get the name of the project
- property prompt: str
Get the prompt of the version
- property recording_count: int
Get the number of recordings in the version