Skip to content

OpenAI TTS

OpenAITTSModel

Bases: TTSModel

A text-to-speech model for OpenAI.

Source code in src/agents/voice/models/openai_tts.py 
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
class OpenAITTSModel(TTSModel):
    """A text-to-speech model for OpenAI."""

    def __init__(
        self,
        model: str,
        openai_client: AsyncOpenAI,
    ):
        """Create a new OpenAI text-to-speech model.

        Args:
            model: The name of the model to use.
            openai_client: The OpenAI client to use.
        """
        self.model = model
        self._client = openai_client

    @property
    def model_name(self) -> str:
        return self.model

    async def run(self, text: str, settings: TTSModelSettings) -> AsyncIterator[bytes]:
        """Run the text-to-speech model.

        Args:
            text: The text to convert to speech.
            settings: The settings to use for the text-to-speech model.

        Returns:
            An iterator of audio chunks.
        """
        response = self._client.audio.speech.with_streaming_response.create(
            model=self.model,
            voice=settings.voice or DEFAULT_VOICE,
            input=text,
            response_format="pcm",
            extra_body={
                "instructions": settings.instructions,
            },
        )

        async with response as stream:
            async for chunk in stream.iter_bytes(chunk_size=1024):
                yield chunk

__init__ 

__init__(model: str, openai_client: AsyncOpenAI)

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 
14
15
16
17
18
19
20
21
22
23
24
25
26
def __init__(
    self,
    model: str,
    openai_client: AsyncOpenAI,
):
    """Create a new OpenAI text-to-speech model.

    Args:
        model: The name of the model to use.
        openai_client: The OpenAI client to use.
    """
    self.model = model
    self._client = openai_client

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.
Source code in src/agents/voice/models/openai_tts.py 
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
async def run(self, text: str, settings: TTSModelSettings) -> AsyncIterator[bytes]:
    """Run the text-to-speech model.

    Args:
        text: The text to convert to speech.
        settings: The settings to use for the text-to-speech model.

    Returns:
        An iterator of audio chunks.
    """
    response = self._client.audio.speech.with_streaming_response.create(
        model=self.model,
        voice=settings.voice or DEFAULT_VOICE,
        input=text,
        response_format="pcm",
        extra_body={
            "instructions": settings.instructions,
        },
    )

    async with response as stream:
        async for chunk in stream.iter_bytes(chunk_size=1024):
            yield chunk