fix(elevenlabs): populate SpeechData.confidence from Scribe logprobs

[rosetta-livekit-bot]

Summary

Ports livekit/agents#6461 to populate ElevenLabs Scribe transcription confidence from spoken-word log probabilities for both batch and realtime STT responses.

Adds a patch changeset for @livekit/agents-plugin-elevenlabs.

Validation

• pnpm build
• pnpm exec vitest run plugins/elevenlabs (19 passed, 2 credential-gated tests skipped)
• pnpm lint
• pnpm format:check

Source diff coverage

• livekit-plugins/livekit-plugins-elevenlabs/livekit/plugins/elevenlabs/stt.py: Adapted to plugins/elevenlabs/src/stt.ts. The Python helper is translated to an internal TypeScript geometric-mean calculation, the target response parser is extended to retain Scribe's type and logprob fields, and confidence is wired into both batch and realtime SpeechData construction.
• tests/test_plugin_elevenlabs_stt.py: Adapted to plugins/elevenlabs/src/stt.test.ts. All four source test cases are preserved in Vitest form; the three helper cases run through batch recognition to avoid exposing an internal helper as public API, and the committed-transcript case runs through the realtime WebSocket path.
• Not applicable: None. Every source file and behavior has a target counterpart, with no infrastructure gaps.

---

Ported from livekit/agents#6461

Original PR description

What / Why

The ElevenLabs STT plugin never populates SpeechData.confidence, so it always stays at its 0.0 default — even though Scribe returns a per-word logprob in every response. Consumers that use confidence (e.g. to tell a clean transcript from a low-confidence / garbled one) get no signal from ElevenLabs.

Verified live: both scribe_v1/scribe_v2 (REST) and scribe_v2_realtime return a natural-log logprob per words[] token, but _process_stream_event / _transcription_to_speech_event read only text + word start/end, so it is discarded and confidence stays 0.0.

Change

Add _speech_confidence(words): average the spoken-word (type == "word") logprobs and exponentiate → a [0, 1] confidence (geometric mean of the token probabilities). Returns 0.0 when per-word logprobs aren't available (e.g. a non-timestamped commit), so behaviour is unchanged there.

Wired into both the REST and WebSocket SpeechData construction.

Note: this deliberately does not use Scribe's language_probability — that is language-identification confidence, a different quantity from transcription confidence, so folding it into SpeechData.confidence would be misleading.

Same class of fix as #5829 / #5830 (a sibling STT plugin not threading its confidence into SpeechData).

Tests

Unit tests for the helper (confident vs low-confidence logprobs, no-logprob → 0.0) and an end-to-end check that a committed transcript sets confidence. ruff check / ruff format clean.

🤖 Generated with Claude Code

[changeset-bot]

🦋 Changeset detected

Latest commit: 0675840

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 39 packages

Name	Type
@livekit/agents-plugin-elevenlabs	Patch
@livekit/agents	Patch
@livekit/agents-plugin-anam	Patch
@livekit/agents-plugin-anthropic	Patch
@livekit/agents-plugin-assemblyai	Patch
@livekit/agents-plugin-azure	Patch
@livekit/agents-plugin-baseten	Patch
@livekit/agents-plugin-bey	Patch
@livekit/agents-plugin-cartesia	Patch
@livekit/agents-plugin-cerebras	Patch
@livekit/agents-plugin-deepgram	Patch
@livekit/agents-plugin-did	Patch
@livekit/agents-plugin-fishaudio	Patch
@livekit/agents-plugin-google	Patch
@livekit/agents-plugin-hedra	Patch
@livekit/agents-plugin-hume	Patch
@livekit/agents-plugin-inworld	Patch
@livekit/agents-plugin-krisp	Patch
@livekit/agents-plugin-lemonslice	Patch
@livekit/agents-plugin-liveavatar	Patch
@livekit/agents-plugin-livekit	Patch
@livekit/agents-plugin-minimax	Patch
@livekit/agents-plugin-mistral	Patch
@livekit/agents-plugin-mistralai	Patch
@livekit/agents-plugin-neuphonic	Patch
@livekit/agents-plugin-openai	Patch
@livekit/agents-plugin-perplexity	Patch
@livekit/agents-plugin-phonic	Patch
@livekit/agents-plugin-protoface	Patch
@livekit/agents-plugin-resemble	Patch
@livekit/agents-plugin-rime	Patch
@livekit/agents-plugin-runway	Patch
@livekit/agents-plugin-sarvam	Patch
@livekit/agents-plugin-silero	Patch
@livekit/agents-plugin-soniox	Patch
@livekit/agents-plugin-tavus	Patch
@livekit/agents-plugin-trugen	Patch
@livekit/agents-plugin-xai	Patch
@livekit/agents-plugins-test	Patch

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

[devin-ai-integration]

✅ Devin Review: No Issues Found

Devin Review analyzed this PR and found no bugs or issues to report.