feat(elevenlabs): support previous text for realtime STT - #2129
Open
rosetta-livekit-bot[bot] wants to merge 1 commit into
Open
feat(elevenlabs): support previous text for realtime STT#2129rosetta-livekit-bot[bot] wants to merge 1 commit into
rosetta-livekit-bot[bot] wants to merge 1 commit into
Conversation
🦋 Changeset detectedLatest commit: e9ce1fa The changes in this PR will be included in the next version bump. This PR includes changesets to release 39 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
previousTextto ElevenLabs STT options, keeping it forscribe_v2_realtimeand warning/ignoring it for non-realtime models.previous_textonce as the first realtimeinput_audio_chunkon websocket connections.@livekit/agents-plugin-elevenlabs.Source diff coverage
Coverage classification
livekit-plugins/livekit-plugins-elevenlabs/livekit/plugins/elevenlabs/stt.py: ported toplugins/elevenlabs/src/stt.ts. Pythonprevious_textmaps to JSpreviousText; constructor warning/ignore behavior maps directly; realtime websocket sends an initial emptyinput_audio_chunkwithprevious_textbefore any audio/keepalive task.tests/test_plugin_elevenlabs_stt.py: adapted toplugins/elevenlabs/src/stt.test.ts. JS private fields prevent direct_optsassertions, so the realtime retention assertion is adapted to observe the first websocket message; the non-realtime ignore/warning assertion is ported by spying on the package logger.Testing
pnpm test plugins/elevenlabs/src/stt.test.tspnpm --filter @livekit/agents-plugin-elevenlabs buildpnpm --filter @livekit/agents-plugin-elevenlabs lintpnpm test plugins/elevenlabspnpm buildpnpm lint(passes with existing warnings)pnpm --filter @livekit/agents-plugin-elevenlabs api:check(fails because this package has no checked-in API report, with existing missing release-tag warnings)Ported from livekit/agents#6534
Original PR description
Summary
previous_textto ElevenLabs realtime STT (scribe_v2_realtime)input_audio_chunkso it is always the first chunk on the connection (ElevenLabs requires this)Fixes #6074
Test plan
uv run pytest tests/test_plugin_elevenlabs_stt.py --plugin elevenlabs