类class
agentscope.ttsGeminiTTSModel
class GeminiTTSModel(TTSModelBase)源码Source
agentscope/tts/_gemini/_model.py:51–329Gemini 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。
Gemini TTS model implementation using the generateContent API with responseModalities: ["AUDIO"]. 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 Gemini TTS models. |
构造器摘要Constructor Summary
| 构造器Constructor | 说明Description |
|---|---|
def __init__(credential: GeminiCredential, model: str = 'gemini-2.5-flash-preview-tts', parameters: 'GeminiTTSModel.Par… | 初始化 `GeminiTTSModel` 实例。 Initialize the Gemini TTS model. |
属性摘要Attribute Summary
| 属性Attribute | 类型Type | 说明Description | 值Value |
|---|---|---|---|
type | Literal['gemini_tts'] | 类型字段。 | 'gemini_tts' |
realtime | bool | 实时字段。 | False |
方法摘要Method Summary
| 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 Gemini TTS API to synthesize speech from text. |
构造器详情Constructor Detail
GeminiTTSModel
def __init__(credential: GeminiCredential, model: str = 'gemini-2.5-flash-preview-tts', parameters: 'GeminiTTSModel.Parameters | None' = None, stream: bool = False, client_kwargs: dict[str, Any] | None = None) -> None初始化 GeminiTTSModel 实例。
Initialize the Gemini TTS model.
说明Notes
- 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 | GeminiCredential | 凭证对象（类型 `GeminiCredential`）。The Google Gemini credential used to authenticate the API call. |
model默认default 'gemini-2.5-flash-preview-tts' | str | 模型实例（类型 `str`）。The TTS model name. Supported models include `gemini-2.5-flash-preview-tts` and `gemini-2.5-pro-preview-tts`. |
parameters默认default None | 'GeminiTTSModel.Parameters | None' | 参数（类型 `'GeminiTTSModel.Parameters | None'`）。The TTS parameters (voice, etc.). When `None`, the default parameters will be used. |
stream默认default False | bool | 流（类型 `bool`）。Whether to use streaming output. When `True`, :meth:`synthesize` returns an async generator yielding incremental `TTSResponse` chunks (see the `streaming document `_); when `False`, it returns a single aggregated `TTSResponse`. |
client_kwargs默认default None | dict[str, Any] | None | 客户端关键字参数（类型 `dict[str, Any] | None`）。Extra keyword arguments forwarded to `google.genai.Client` (e.g. `vertexai`, `project`, `location`, `credentials`, `http_options`). |
源码Source
agentscope/tts/_gemini/_model.py:72–117属性详情Attribute Detail
type
Literal['gemini_tts'] = 'gemini_tts'类型字段。声明为 Literal['gemini_tts']。
The type field.
源码Source
agentscope/tts/_gemini/_model.py:67realtime
bool = False实时字段。声明为 bool。
The realtime field.
源码Source
agentscope/tts/_gemini/_model.py:70方法详情Method Detail
synthesize
async def synthesize(text: str | None = None, **kwargs: Any) -> TTSResponse | AsyncGenerator[TTSResponse, None]async
执行 synthesize 方法。
Call the Gemini TTS 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. |
TTSResponse | AsyncGenerator[TTSResponse, None]
返回TTSResponse|AsyncGenerator[TTSResponse,None]。`TTSResponse | AsyncGenerator[TTSResponse, None]`:
源码Source
agentscope/tts/_gemini/_model.py:119–179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 Gemini TTS models. Declared in agentscope.tts.