Sending audio to Tavus using custom tracks #1950
Open
Conversation
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
Codecov ReportAttention: Patch coverage is
... and 2 files with indirect coverage changes 🚀 New features to boost your workflow:
|
…stead of `app-messages`
… instead of `app-messages`
8de4d1a to
9f4fed2
Compare
aconchillo
reviewed
Jun 4, 2025
aconchillo
reviewed
Jun 4, 2025
aconchillo
reviewed
Jun 4, 2025
aconchillo
reviewed
Jun 4, 2025
aconchillo
reviewed
Jun 4, 2025
aconchillo
reviewed
Jun 4, 2025
|
Nice cleanup! Added some comments. |
aconchillo
reviewed
Jun 11, 2025
| - `TavusTransport` and `TavusVideoService` now send audio to Tavus using WebRTC | ||
| audio tracks instead of `app-messages` over WebSocket. This should improve the | ||
| overall audio quality. | ||
| - |
There was a problem hiding this comment.
This probably needs a rebase.
aconchillo
reviewed
Jun 11, 2025
| @@ -58,7 +54,7 @@ def __init__( | |||
| *, | |||
| api_key: str, | |||
| replica_id: str, | |||
| persona_id: str = "pipecat0", # Use `pipecat0` so that your TTS voice is used in place of the Tavus persona | |||
| persona_id: str = "pipecat-stream", | |||
There was a problem hiding this comment.
The docstring above needs to be updated with pipecat-stream
aconchillo
reviewed
Jun 11, 2025
| @@ -133,15 +142,14 @@ def __init__( | |||
| callbacks: TavusCallbacks, | |||
| api_key: str, | |||
| replica_id: str, | |||
| persona_id: str = "pipecat0", # Use `pipecat0` so that your TTS voice is used in place of the Tavus persona | |||
| persona_id: str = "pipecat-stream", | |||
There was a problem hiding this comment.
The docstring above needs to mention pipecat-stream
aconchillo
approved these changes
Jun 11, 2025
|
LGTM. Just 3 minor comments about CHANGELOG and docstrings. Nice work! 🙌 |
filipi87
commented
Jun 12, 2025
| @@ -767,6 +767,7 @@ async def add_custom_audio_track(self, track_name: str) -> DailyAudioTrack: | |||
| self._client.add_custom_audio_track( | |||
| track_name=track_name, | |||
| audio_track=audio_track, | |||
| ignore_audio_level=True, | |||
There was a problem hiding this comment.
This is preventing the SFU to use the custom audio tracker to trigger the active speaker event.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This PR adds support for sending audio to Tavus using custom tracks instead of app messages.
It also includes a test script (
scripts/test_tavus_transport.py) that mimics the behavior expected to be supported by Tavus.