Audio Transcriptions

Audio transcription converts spoken words from an audio recording into written text. Common uses include:

Transcribing meetings, interviews, and conversations into written form.
Making content accessible to people who are deaf or hard of hearing.
Creating written versions of podcasts, videos, and interviews for repurposing and sharing.
Improving search engine optimization (SEO) by providing indexable text for audio content.
Analyzing spoken data such as research interviews and user feedback.

Audio transcriptions are served by OpenAI models through the endpoint below.

Request

URL: https://ai.purlabs.xyz/openai/audio/transcriptions

Request Method: POST

TS Request Interface


interface Request {
  file: string;
  model: string;
  prompt?: string;
  response_format?: string;
  temperature?: number;
  language?: string;
}

Request API Reference

Property	Type	Required	Description
`file`	`File`	Required	The audio file object (not file name) to transcribe, in one of these formats: `flac`, `mp3`, `mp4`, `mpeg`, `mpga`, `m4a`, `ogg`, `wav`, or `webm`.
`model`	`string`	Required	ID of the model to use. Only `whisper-1` is currently available.
`prompt`	`string`	Optional	An optional text to guide the model’s style or continue a previous audio segment. The prompt should match the audio language.
`response_format`	`string`	Optional	Defaults to `json`. The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.
`temperature`	`number`	Optional	Defaults to `0`. 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.
`language`	`string`	Optional	The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

Example JSON Request Body


{
  "file": "https://my-audio-sample.com/audio.mp3",
  "model": "whisper-1",
  "response_format": "json"
}

Response

TS Response Interface


interface Response {
  text: string;
};

Example JSON Response


{
  "text": "Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that."
}