feat: Gemini TTS #4307
Open
feat: Gemini TTS #4307
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
dirkbrnd
reviewed
Aug 23, 2025
libs/agno/agno/media.py
Outdated
| @@ -211,22 +211,41 @@ def from_artifact(cls, artifact: AudioArtifact) -> "Audio": | |||
|
|
|||
| class AudioResponse(BaseModel): | |||
| id: Optional[str] = None | |||
| content: Optional[str] = None # Base64 encoded | |||
| content: Optional[str] = None # Base64 encoded (legacy) | |||
There was a problem hiding this comment.
Why is this legacy? In other cases we get base64 data
dirkbrnd
reviewed
Aug 23, 2025
dirkbrnd
reviewed
Aug 23, 2025
libs/agno/agno/utils/audio.py
Outdated
| @@ -20,3 +21,27 @@ def write_audio_to_file(audio, filename: str): | |||
| with open(filename, "wb") as f: | |||
| f.write(wav_bytes) | |||
| log_info(f"Audio file saved to {filename}") | |||
|
|
|||
|
|
|||
| def save_wave_file(filename: str, pcm_data: bytes, channels: int = 1, rate: int = 24000, sample_width: int = 2): | |||
There was a problem hiding this comment.
Suggested change
| def save_wave_file(filename: str, pcm_data: bytes, channels: int = 1, rate: int = 24000, sample_width: int = 2): | |
| def write_wav_audio_to_file(filename: str, pcm_data: bytes, channels: int = 1, rate: int = 24000, sample_width: int = 2): |
dirkbrnd
reviewed
Aug 23, 2025
| # Store raw binary data | ||
| model_response.audio = AudioResponse( | ||
| id=str(uuid4()), | ||
| raw_content=part.inline_data.data, # Raw binary data |
There was a problem hiding this comment.
Lets just re-use content param?
I think generally we should decode audio that we get in base64, so here it is raw (nice, store as is) and then we can update OpenAI that we decode the audio before storing it in AudioResponse, so it is always "raw" when coming from Agno.
But lets do the OpenAI part later. Regardless, lets just use content for both.
There was a problem hiding this comment.
makes sense. TODO: OpenAI change
dirkbrnd
reviewed
Sep 3, 2025
| expires_at: Optional[int] = None | ||
| transcript: Optional[str] = None | ||
|
|
||
| mime_type: Optional[str] = None | ||
| sample_rate: Optional[int] = 24000 | ||
| channels: Optional[int] = 1 | ||
|
|
||
| @property | ||
| def binary_data(self) -> bytes: |
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.
Summary
Adds support for Gemini TTS.
TODO: OpenAI update
Type of change
Checklist
./scripts/format.shand./scripts/validate.sh)