Skip to main content
The TypeScript SDK and docs are currently in beta. Report issues on GitHub.
Speech-to-text request input. Accepts a JSON body with input_audio containing base64-encoded audio.

​
Example Usage

import { STTRequest } from "@openrouter/sdk/models";

let value: STTRequest = {
  inputAudio: {
    data: "UklGRiQA...",
    format: "wav",
  },
  model: "openai/whisper-large-v3",
};

​
Fields

FieldTypeRequiredDescriptionExample
inputAudiomodels.STTInputAudio:heavy_check_mark:Base64-encoded audio to transcribe{"data": "UklGRiQA...","format": "wav"}
languagestring:heavy_minus_sign:ISO-639-1 language code (e.g., “en”, “ja”). Auto-detected if omitted.en
modelstring:heavy_check_mark:STT model identifieropenai/whisper-large-v3
providermodels.STTRequestProvider:heavy_minus_sign:Provider-specific passthrough configuration
temperaturenumber:heavy_minus_sign:Sampling temperature for transcription0