类class agentscope.tts

DashScopeCosyVoiceTTSModel

class DashScopeCosyVoiceTTSModel(TTSModelBase)

源码Source agentscope/tts/_dashscope/_cosyvoice_model.py:30–397

DashScope Cosy 语音 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 list_models、synthesize、connect、close、push。

DashScope CosyVoice TTS model using the WebSocket SpeechSynthesizer. 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 DashScope CosyVoice TTS models.

构造器摘要Constructor Summary

构造器Constructor	说明Description
`def __init__(credential:` `DashScopeCredential, model: str = 'cosyvoice-v3-flash', parameters: 'DashScopeCosyVoiceTTSMode…`	初始化 `DashScopeCosyVoiceTTSModel` 实例。 Initialize the DashScope CosyVoice TTS model.

属性摘要Attribute Summary

属性Attribute	类型Type	说明Description	值Value
`type`	Literal['dashscope_cosyvoice_tts']	类型字段。	`'dashscope_cosyvoice_tts'`

方法摘要Method Summary

方法Method	说明Description
`def list_models(custom_yaml_dir: str \| None = None) -> list[TTSModelCard]`	列出模型。 List CosyVoice model cards from the dedicated card directory.
`async def synthesize(text: str \| None = None, **kwargs: Any) ->` `TTSResponse \| AsyncGenerator[TTSResponse, None]`async	执行 `synthesize` 方法。 Call the DashScope CosyVoice TTS API to synthesize speech.
`async def connect() -> None`async	用于实时模式的初始化 SpeechSynthesizer。 Initialize the SpeechSynthesizer for realtime mode.
`async def close() -> None`async	关闭连接并释放相关资源。 Close the realtime SpeechSynthesizer.
`async def push(text: str, **kwargs: Any) ->` `TTSResponse`async	执行推送相关操作。 Push an incremental text delta for realtime synthesis.

构造器详情Constructor Detail

DashScopeCosyVoiceTTSModel

def __init__(credential: DashScopeCredential, model: str = 'cosyvoice-v3-flash', parameters: 'DashScopeCosyVoiceTTSModel.Parameters | None' = None, stream: bool = True, cold_start_length: int | None = None, cold_start_words: int | None = None, max_retries: int = 3, retry_delay: float = 5.0) -> None

初始化 DashScopeCosyVoiceTTSModel 实例。

Initialize the DashScope CosyVoice TTS model.

参数Parameters

名称Name	类型Type	说明Description
`credential`	DashScopeCredential	凭证对象（类型 `DashScopeCredential`）。The DashScope credential used to authenticate the API call.
`model`默认default `'cosyvoice-v3-flash'`	str	CosyVoice 模型名称。The CosyVoice model name.
`parameters`默认default `None`	'DashScopeCosyVoiceTTSModel.Parameters \| None'	参数（类型 `'DashScopeCosyVoiceTTSModel.Parameters \| None'`）。The TTS parameters. When `None`, the default voice is used.
`stream`默认default `True`	bool	流（类型 `bool`）。Whether :meth:`synthesize` returns an async generator yielding `TTSResponse` chunks. When `False`, audio is aggregated.
`cold_start_length`默认default `None`	int \| None	cold 启动长度（类型 `int \| None`）。Minimum character count before the first realtime text chunk is sent to the synthesizer.
`cold_start_words`默认default `None`	int \| None	cold 启动 words（类型 `int \| None`）。Minimum word count before the first realtime text chunk is sent.
`max_retries`默认default `3`	int	最大重试次数（类型 `int`）。Max retry attempts on realtime synthesis failure.
`retry_delay`默认default `5.0`	float	重试延迟（类型 `float`）。Initial retry delay in seconds (exponential backoff).

源码Source agentscope/tts/_dashscope/_cosyvoice_model.py:52–104

属性详情Attribute Detail

type

Literal['dashscope_cosyvoice_tts'] = 'dashscope_cosyvoice_tts'

类型字段。声明为 Literal['dashscope_cosyvoice_tts']。

The type field.

源码Source agentscope/tts/_dashscope/_cosyvoice_model.py:47

方法详情Method Detail

list_models

def list_models(custom_yaml_dir: str | None = None) -> list[TTSModelCard]

列出模型。

List CosyVoice model cards from the dedicated card directory.

参数Parameters

名称Name	类型Type	说明Description
`custom_yaml_dir`默认default `None`	str \| None	自定义 yaml 目录（类型 `str \| None`）。The custom yaml dir.

返回Returns list[TTSModelCard]

返回TTSModelCard列表。Returns a list of TTS model card.

源码Source agentscope/tts/_dashscope/_cosyvoice_model.py:107–114

synthesize

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

async

执行 synthesize 方法。

Call the DashScope CosyVoice TTS API to synthesize speech.

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/_dashscope/_cosyvoice_model.py:116–139

connect

async def connect() -> None

async

用于实时模式的初始化 SpeechSynthesizer。

Initialize the SpeechSynthesizer for realtime mode.

返回Returns None

无返回值。No value is returned.

源码Source agentscope/tts/_dashscope/_cosyvoice_model.py:187–194

close

async def close() -> None

async

关闭连接并释放相关资源。

Close the realtime SpeechSynthesizer.

返回Returns None

无返回值。No value is returned.

源码Source agentscope/tts/_dashscope/_cosyvoice_model.py:196–205

push

async def push(text: str, **kwargs: Any) -> TTSResponse

async

执行推送相关操作。

Push an incremental text delta for realtime synthesis.

参数Parameters

名称Name	类型Type	说明Description
`text`	str	文本（类型 `str`）。The text.
`kwargs`	Any	关键字参数（类型 `Any`）。The kwargs.

返回Returns TTSResponse

返回TTSResponse。Returns TTS response.

源码Source agentscope/tts/_dashscope/_cosyvoice_model.py:219–261

嵌套类详情Nested Class Detail

Parameters

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 DashScope CosyVoice TTS models. Declared in agentscope.tts.

继承成员Inherited Members

继承自Inherited from TTSModelBase

__aenter__, __aexit__, credential, model, parameters, stream, realtime