Skip to content

feat(elevenlabs): stream eleven_v3/eleven_v3_conversational via text-to-dialogue #6838

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ameyakhare wants to merge 5 commits into
base: main
Choose a base branch
from
+819 −22
Open

feat(elevenlabs): stream eleven_v3/eleven_v3_conversational via text-to-dialogue #6838

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
fa13eaa
feat(elevenlabs): stream eleven_v3/eleven_v3_conversational via text-…
ameyakhare Aug 13, 2026
ba303fb
fix(elevenlabs): address Devin review findings on dialogue connection
ameyakhare Aug 13, 2026
b7e4f0b
fix(elevenlabs): track flush/turn-boundary counts and avoid self-canc…
ameyakhare Aug 13, 2026
287e66a
fix(elevenlabs): sync drain event before waiting so an unflushed clos…
ameyakhare Aug 13, 2026
7d460c9
fix(elevenlabs): skip the drain wait when a dialogue stream is interr…
ameyakhare Aug 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions livekit-plugins/livekit-plugins-elevenlabs/livekit/plugins/elevenlabs/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,18 @@
"eleven_flash_v2_5",
"eleven_flash_v2",
"eleven_v3",
"eleven_v3_conversational",
]

# Synthesized via text-to-dialogue instead of text-to-speech (see tts.py).
DIALOGUE_TTS_MODEL_PREFIX = "eleven_v3"


def is_dialogue_model(model: str) -> bool:
"""Whether `model` must be synthesized via the text-to-dialogue API."""
return model.startswith(DIALOGUE_TTS_MODEL_PREFIX)
Comment thread
devin-ai-integration[bot] marked this conversation as resolved.


# https://elevenlabs.io/docs/api-reference/text-to-speech/convert#request.query.output_format
TTSEncoding = Literal[
"mp3_22050_32",
Expand Down
Loading