Skip to content

Feat/elevenlabs live - #3086

Open
stepacool wants to merge 6 commits into
ag2ai:mainfrom
stepacool:feat/elevenlabs-live
Open

Feat/elevenlabs live#3086
stepacool wants to merge 6 commits into
ag2ai:mainfrom
stepacool:feat/elevenlabs-live

Conversation

@stepacool

Copy link
Copy Markdown
Contributor

Why are these changes needed?

Issue was open (#3039)
11labs is one of the best/main voice providers out there.

Changes are the implementation of Elevenlabs STT/TTS within the current ag2's architecture of voice - meaning no VAD/turn taking in Pipe/Cascade. For that reason, streaming of STT is not implemented(doesn't align with the current agent/voice/pipe implementation, no support for interruptions etc.)

But added support

Related issue number

Closes #3039

Checks

AI assistance

  • [y] I understand the changes in this PR and can explain them in my own words.
  • [y] I have verified that the PR description accurately reflects the actual diff.
  • [y] If AI assistance was used, I reviewed, tested, and validated the generated code/text before submitting.

@github-actions github-actions Bot added area:docs Documentation (website/) area:deps Python dependency updates (pyproject.toml, uv.lock) labels Jul 19, 2026
@stepacool
stepacool force-pushed the feat/elevenlabs-live branch from bca7bf0 to 49fc19d Compare July 19, 2026 15:55
@github-actions github-actions Bot added the area:core Agent runtime core: ag2/*.py, ag2/events, ag2/response, ag2/streams label Jul 19, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area:core Agent runtime core: ag2/*.py, ag2/events, ag2/response, ag2/streams area:deps Python dependency updates (pyproject.toml, uv.lock) area:docs Documentation (website/)

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add ElevenLabs-based STT and TTS implementations as alternatives to OpenAITranscriber and OpenAITTSConfig

1 participant