Skip to content

feat(stt): add ElevenLabs Scribe v2 provider - #28167

Closed
haayhappen wants to merge 1 commit into
NousResearch:mainfrom
haayhappen:feat/elevenlabs-scribe-stt
Closed

feat(stt): add ElevenLabs Scribe v2 provider#28167
haayhappen wants to merge 1 commit into
NousResearch:mainfrom
haayhappen:feat/elevenlabs-scribe-stt

Conversation

@haayhappen

Copy link
Copy Markdown

Summary

  • Add explicit stt.provider: elevenlabs using ElevenLabs batch POST /v1/speech-to-text with default model scribe_v2
  • Reuse ELEVENLABS_API_KEY; config under stt.elevenlabs (language, base_url, tag_audio_events, diarize)
  • Explicit opt-in only (not in auto-detect chain)
  • Tests, docs, dashboard STT provider option

Test plan

  • scripts/run_tests.sh tests/tools/test_transcription_tools.py tests/tools/test_transcription_dotenv_fallback.py -q
  • Set stt.provider: elevenlabs + ELEVENLABS_API_KEY, send a voice message on Telegram/Discord
  • Confirm voice mode / gateway transcribes successfully

Added support for ElevenLabs Scribe v2 in the speech-to-text functionality, enhancing transcription capabilities. Updated configuration options to include ElevenLabs, modified relevant documentation, and implemented tests to ensure proper integration. This addition allows users to leverage ElevenLabs' advanced transcription services, requiring the ELEVENLABS_API_KEY for access.

@BoardJames-Bot BoardJames-Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Reviewed by Hermes Agent. Diff is coherent: ElevenLabs Scribe is explicit opt-in, key/base-url handling uses the existing env/config paths, request/response errors fail closed, and focused transcription tests pass locally (120 passed). No blockers. Note: repo currently exposes no status checks on this PR, and BoardJames-Bot has pull-only repo permission so I cannot merge.

@alt-glitch alt-glitch added type/feature New feature or request tool/tts Text-to-speech and transcription comp/cli CLI entry point, hermes_cli/, setup wizard P3 Low — cosmetic, nice to have labels May 18, 2026
@alt-glitch

Copy link
Copy Markdown
Collaborator

Duplicate of #19777 (ElevenLabs Scribe STT with multi-key quota fallback — same scribe_v2 model, same feature). Also see closed #26526 which was superseded by #19777 for the same reason.

@haayhappen

Copy link
Copy Markdown
Author

Superseded by #19777

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

comp/cli CLI entry point, hermes_cli/, setup wizard P3 Low — cosmetic, nice to have tool/tts Text-to-speech and transcription type/feature New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants