When to Use SAA
Model Requirement
SAA requires one of:model_id, the persisted SAA workflow defaults to
Granite-Speech-4.1-2B-Plus. Supplying any other model returns a validation
error.
Nemotron-3.5-Transcribe-30B-A4B-FP8 needs about 32 GiB of memory (see Transcription).
It tags speakers as it transcribes, in one pass of up to 60 minutes. Its turns
are labelled “Speaker 1”, “Speaker 2” and so on, and carry start and end times
when its own word timestamps align. It labels speakers in Arabic, Chinese,
English, French, German, Hindi, Italian, Japanese, Korean, Portuguese, Russian,
Spanish and Thai. The speaker expectation does not steer it: a speaker count
outside min_speakers or max_speakers only adds a warning to the record.
Using the Web UI
- Open Transcription in the sidebar.
- Choose Speaker Attributed ASR from the mode switch.
- Upload or record audio.
- Select a ready speaker-attributed model.
- Choose a speaker expectation: Auto, 2+, 3+, or 4+.
- Optionally enable summary generation.
- Submit the job and review the speaker-turn transcript.
Using the API
Create a persisted SAA job withjob_kind=speaker_attributed_asr:
job_kind=saa is also accepted.
Poll the returned record until processing_status is ready:
Request Fields
JSON and multipart create requests accept:
Unsupported for SAA:
streaminclude_timestampsword_timestampsaligner_model_id