dtkt.ai.v1beta1messages.protoStreamSpeechRequest
Message| Field | Type | Number | Description |
|---|---|---|---|
| text | string | 1 | No description. |
| messages | Message[] dtkt.ai.v1beta1.Message[] | 2 | The input messages / prompts to be synthesized into speech |
| voice | string | 3 | Provider specific voice identifier |
| output_media_type | string | 4 | Output media type, e.g., "audio/mpeg", "audio/wav", "audio/ogg" |
| speed | float | 5 | Speech synthesis speed; range and meaning may vary by provider. |
| language | string | 6 | The language (input and output); an ISO-639-1 language code or 'auto' to auto-detect. Provider support may vary. |
| provider_options | Struct google.protobuf.Struct | 10 | No description. |