Add hosted Oruk API STT plugin - #7501
Draft
Nathan-Roll1 wants to merge 2 commits into
Draft
Nathan-Roll1 wants to merge 2 commits into
Nathan-Roll1 wants to merge 2 commits into
Conversation
This branch has not been deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds an authenticated Oruk API STT provider and a runnable WAV example, following the request for a hosted Python integration. Spectra-2 returns a final utterance; live agents use the existing VAD StreamAdapter. The plugin converts input to mono 16 kHz, preserves request identity/audio across transport retries, handles the API's distinct capacity-rejection rules, and avoids replaying authentication, completed/uncertain-ID, or malformed-success failures.
Validation: 31 focused plugin/base/prewarm tests pass; package wheel and sdist build; repository formatting and lint pass. A dedicated temporary internal key completed three real API calls (six public-fixture audio seconds), including 48 kHz stereo input conversion; automatic retries were disabled for that smoke. Full repository mypy reports the same 14 Azure/AWS dependency errors with this plugin excluded; the new plugin's focused strict check passes. Upstream CI passes repository lint, Python 3.10/3.13 typing, all three platform blockguard suites, the release gate, CLA and the broad unit suite. No native partial streaming, diarization, word alignment, or latency/accuracy guarantee is claimed.
Run before publication:
uv sync --package livekit-agents --extra oruk --extra silero --dev, setORUK_API_KEY, thenuv run python examples/other/oruk_transcribe.py recording.wav. The account must have access to the selected model.