DocumentationAPI reference
Rust · 0.1.0
InstanceSetting_TranscriptionConfig
Application protocol schema. Field names and inherited descriptions are kept in their original language.
Where this schema is used
These links are derived from direct references in the protocol snapshot. Follow the calling operation for authentication, accepted fields and runtime behavior; a reusable resource schema is not by itself a complete write request.
Referenced by these component schemas:
Shape and fields
object
TranscriptionConfig configures the speech-to-text feature.
| Field | Type / requirement | Description |
|---|---|---|
providerId | string | provider_id references an entry in AISetting.providers[].id. Empty string means transcription is disabled. |
model | string | model is the provider-specific model identifier. Empty string falls back to the engine default (whisper-1 for OPENAI providers, gemini-2.5-flash for GEMINI providers). |
language | string | language is the default ISO 639-1 language hint sent to the provider. Empty string lets the provider auto-detect. |
prompt | string | prompt is a default spelling/vocabulary hint passed to the provider. |
Complete schema
Use this complete JSON definition for constraints and nested structure. A field's presence here does not mean it is writable by every caller.
{
"type": "object",
"properties": {
"providerId": {
"type": "string",
"description": "provider_id references an entry in AISetting.providers[].id.\n Empty string means transcription is disabled."
},
"model": {
"type": "string",
"description": "model is the provider-specific model identifier.\n Empty string falls back to the engine default\n (whisper-1 for OPENAI providers, gemini-2.5-flash for GEMINI providers)."
},
"language": {
"type": "string",
"description": "language is the default ISO 639-1 language hint sent to the provider.\n Empty string lets the provider auto-detect."
},
"prompt": {
"type": "string",
"description": "prompt is a default spelling/vocabulary hint passed to the provider."
}
},
"description": "TranscriptionConfig configures the speech-to-text feature."
}