类class
agentscope.ttsParameters
class Parameters(BaseModel)源码Source
agentscope/tts/_openai/_model.py:52–81参数，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.
属性摘要Attribute Summary
| 属性Attribute | 类型Type | 说明Description | 值Value |
|---|---|---|---|
voice | str | 语音字段。 | Field(default='alloy', title='Voice', description='The voice to use for synthesis.') |
response_format | Literal['mp3', 'opus', 'aac', 'flac', 'wav', 'pcm'] | 响应格式字段。 | Field(default=_DEFAULT_RESPONSE_FORMAT, title='Response Format', description='The audio format of the synthesized speech.') |
instructions | str | None | 指令字段。 | Field(default=None, title='Instructions', description='Additional instructions for controlling the voice (only supported by some models, e.g. gpt-4o-mini-tts).') |
属性详情Attribute Detail
voice
str = Field(default='alloy', title='Voice', description='The voice to use for synthesis.')语音字段。声明为 str。
The voice to use for synthesis.
源码Source
agentscope/tts/_openai/_model.py:55response_format
Literal['mp3', 'opus', 'aac', 'flac', 'wav', 'pcm'] = Field(default=_DEFAULT_RESPONSE_FORMAT, title='Response Format', description='The audio format of the synthesized speech.')响应格式字段。声明为 Literal['mp3', 'opus', 'aac', 'flac', 'wav', 'pcm']。
The audio format of the synthesized speech.
源码Source
agentscope/tts/_openai/_model.py:61instructions
str | None = Field(default=None, title='Instructions', description='Additional instructions for controlling the voice (only supported by some models, e.g. gpt-4o-mini-tts).')指令字段。声明为 str | None。
Additional instructions for controlling the voice (only supported by some models, e.g.
源码Source
agentscope/tts/_openai/_model.py:74