Interface: OpenAITranscriptionModelSettings
Hierarchy
-
↳
OpenAITranscriptionModelSettings
Properties
api
• Optional api: ApiConfiguration
Defined in
packages/modelfusion/src/model-provider/openai/OpenAITranscriptionModel.ts:29
language
• Optional language: string
The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
Defined in
packages/modelfusion/src/model-provider/openai/OpenAITranscriptionModel.ts:39
model
• model: "whisper-1"
ID of the model to use. Only whisper-1 is currently available.
Defined in
packages/modelfusion/src/model-provider/openai/OpenAITranscriptionModel.ts:34
observers
• Optional observers: FunctionObserver[]
Observers that are called when the model is used in run functions.
Inherited from
TranscriptionModelSettings.observers
Defined in
packages/modelfusion/src/model-function/Model.ts:8
prompt
• Optional prompt: string
An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
Defined in
packages/modelfusion/src/model-provider/openai/OpenAITranscriptionModel.ts:53
temperature
• Optional temperature: number
The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.
Defined in
packages/modelfusion/src/model-provider/openai/OpenAITranscriptionModel.ts:48