类class agentscope.tts

OpenAITTSModel

class OpenAITTSModel(TTSModelBase)

源码Source agentscope/tts/_openai/_model.py:46–256

OpenAI TTS 模型，处理低延迟的实时语音与多模态交互。位于 agentscope.tts 包，继承自 TTSModelBase。核心成员包括 synthesize。

OpenAI TTS model implementation using the Audio Speech API. Declared in agentscope.tts. Extends TTSModelBase.

嵌套类摘要Nested Class Summary

类Class	类型Kind	说明Description
`Parameters`	类class	参数，处理低延迟的实时语音与多模态交互。 Frontend-exposed parameters for OpenAI TTS models.

构造器Constructor	说明Description
`def __init__(credential:` `OpenAICredential, model: str = 'tts-1', parameters: 'OpenAITTSModel.Parameters \| None' = None,…`	初始化 `OpenAITTSModel` 实例。 Initialize the OpenAI TTS model.

属性Attribute	类型Type	说明Description	值Value
`type`	Literal['openai_tts']	类型字段。	`'openai_tts'`
`realtime`	bool	实时字段。	`False`

方法Method	说明Description
`async def synthesize(text: str \| None = None, **kwargs: Any) ->` `TTSResponse \| AsyncGenerator[TTSResponse, None]`async	执行 `synthesize` 方法。 Call the OpenAI Audio Speech API to synthesize speech from text.

def __init__(credential: OpenAICredential, model: str = 'tts-1', parameters: 'OpenAITTSModel.Parameters | None' = None, stream: bool = True) -> None

初始化 OpenAITTSModel 实例。

Initialize the OpenAI TTS model.

注意：该行为受运行时配置或底层实现影响，建议结合对应源码与版本说明确认。Note: More details about the parameters, such as `model` and `voice`, can be found in the `official document `_.

参数Parameters

名称Name	类型Type	说明Description
`credential`	OpenAICredential	凭证对象（类型 `OpenAICredential`）。The OpenAI credential used to authenticate the API call.
`model`默认default `'tts-1'`	str	模型实例（类型 `str`）。The TTS model name. Supported models include `tts-1`, `tts-1-hd` and `gpt-4o-mini-tts`.
`parameters`默认default `None`	'OpenAITTSModel.Parameters \| None'	参数（类型 `'OpenAITTSModel.Parameters \| None'`）。The TTS parameters (voice, response format, etc.). When `None`, the default parameters will be used.
`stream`默认default `True`	bool	流（类型 `bool`）。Whether to use streaming output. When `True`, :meth:`synthesize` returns an async generator yielding `TTSResponse` chunks; when `False`, it returns a single aggregated `TTSResponse`.

源码Source agentscope/tts/_openai/_model.py:88–130

Literal['openai_tts'] = 'openai_tts'

类型字段。声明为 Literal['openai_tts']。

The type field.

源码Source agentscope/tts/_openai/_model.py:83

bool = False

实时字段。声明为 bool。

The realtime field.

源码Source agentscope/tts/_openai/_model.py:86

async def synthesize(text: str | None = None, **kwargs: Any) -> TTSResponse | AsyncGenerator[TTSResponse, None]

async

执行 synthesize 方法。

Call the OpenAI Audio Speech API to synthesize speech from text.

参数Parameters

名称Name	类型Type	说明Description
`text`默认default `None`	str \| None	文本（类型 `str \| None`）。The text to be synthesized.
`kwargs`	Any	关键字参数（类型 `Any`）。The kwargs.

返回Returns TTSResponse | AsyncGenerator[TTSResponse, None]

返回TTSResponse|AsyncGenerator[TTSResponse,None]。`TTSResponse | AsyncGenerator[TTSResponse, None]`:

源码Source agentscope/tts/_openai/_model.py:132–175

class Parameters

参数，处理低延迟的实时语音与多模态交互。位于 agentscope.tts 包。

Frontend-exposed parameters for OpenAI TTS models. Declared in agentscope.tts.

继承自Inherited from TTSModelBase