Skip to content

feat(elevenlabs): add keyterms support to scribe v2 STT #4708

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

Open
MuthanaA wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat(elevenlabs): add keyterms support to scribe v2 STT #4708

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
9 changes: 9 additions & 0 deletions livekit-plugins/livekit-plugins-elevenlabs/livekit/plugins/elevenlabs/stt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,6 +72,7 @@ class STTOptions:
include_timestamps: bool
sample_rate: STTRealtimeSampleRates
server_vad: NotGivenOr[VADOptions | None]
keyterms: list[str] | None


class STT(stt.STT):
Expand All @@ -88,6 +89,7 @@ def __init__(
include_timestamps: bool = False,
http_session: aiohttp.ClientSession | None = None,
model_id: NotGivenOr[ElevenLabsSTTModels | str] = NOT_GIVEN,
keyterms: NotGivenOr[list[str]] = NOT_GIVEN,
) -> None:
"""
Create a new instance of ElevenLabs STT.
Expand All @@ -105,6 +107,9 @@ def __init__(
http_session (aiohttp.ClientSession | None): Custom HTTP session for API requests. Optional.
model_id (ElevenLabsSTTModels | str): ElevenLabs STT model to use. If not specified a default model will
be selected based on parameters provided.
keyterms (NotGivenOr[list[str]]): A list of keyterms to bias the transcription towards.
Only supported for scribe_v2 model. Max 100 terms, each under 50 characters
and at most 5 words.
"""

if is_given(use_realtime):
Expand Down Expand Up @@ -149,6 +154,7 @@ def __init__(
server_vad=server_vad,
include_timestamps=include_timestamps,
model_id=model_id,
keyterms=keyterms or None,
)
self._session = http_session
self._streams = weakref.WeakSet[SpeechStream]()
Expand Down Expand Up @@ -184,6 +190,9 @@ async def _recognize_impl(
form.add_field("tag_audio_events", str(self._opts.tag_audio_events).lower())
if self._opts.language_code:
form.add_field("language_code", self._opts.language_code)
if self._opts.keyterms:
for keyterm in self._opts.keyterms:
form.add_field("keyterms", keyterm)

try:
async with self._ensure_session().post(
Expand Down
Loading