OpenAI TTS
OpenAITTSModel
Bases: TTSModel
A text-to-speech model for OpenAI.
Source code in src/agents/voice/models/openai_tts.py
__init__
Create a new OpenAI text-to-speech model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
model
|
str
|
The name of the model to use. |
required |
openai_client
|
AsyncOpenAI
|
The OpenAI client to use. |
required |
Source code in src/agents/voice/models/openai_tts.py
run
async
run(
text: str, settings: TTSModelSettings
) -> AsyncIterator[bytes]
Run the text-to-speech model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
text
|
str
|
The text to convert to speech. |
required |
settings
|
TTSModelSettings
|
The settings to use for the text-to-speech model. |
required |
Returns:
Type | Description |
---|---|
AsyncIterator[bytes]
|
An iterator of audio chunks. |