Skip to content

feat(assemblyai): add speaker diarization support #5074

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
longcw merged 1 commit into from
Mar 13, 2026
Merged

feat(assemblyai): add speaker diarization support #5074

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions livekit-plugins/livekit-plugins-assemblyai/livekit/plugins/assemblyai/stt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,6 +112,7 @@ def __init__(
interim_results=True,
aligned_transcript="word",
offline_recognize=False,
diarization=is_given(speaker_labels) and speaker_labels is True,
),
)
if model == "u3-pro":
Expand Down Expand Up @@ -500,6 +501,10 @@ def _process_stream_event(self, data: dict) -> None:
transcript = data.get("transcript", "")
language = LanguageCode(data.get("language_code", "en"))

# Extract speaker label for diarization (returns "A", "B", ... or "UNKNOWN")
speaker_label = data.get("speaker_label")
speaker_id = speaker_label if speaker_label and speaker_label != "UNKNOWN" else None

# transcript (final) and words (interim) are cumulative
# utterance (preflight) is chunk based
start_time: float = 0
Expand Down Expand Up @@ -535,6 +540,7 @@ def _process_stream_event(self, data: dict) -> None:
end_time=end_time,
words=timed_words,
confidence=confidence,
speaker_id=speaker_id,
)
],
)
Expand Down Expand Up @@ -565,6 +571,7 @@ def _process_stream_event(self, data: dict) -> None:
end_time=end_time,
words=utterance_words,
confidence=utterance_confidence,
speaker_id=speaker_id,
)
],
)
Expand All @@ -584,6 +591,7 @@ def _process_stream_event(self, data: dict) -> None:
end_time=end_time,
words=timed_words,
confidence=confidence,
speaker_id=speaker_id,
)
],
)
Expand Down