Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.prem.io/llms.txt

Use this file to discover all available pages before exploring further.

​
Basic Audio Transcription

Transcribe audio files to text: 
import createRvencClient from "@premai/api-sdk";
import fs from "fs";

const client = await createRvencClient({
  apiKey: process.env.API_KEY,
  clientKEK: process.env.CLIENT_KEK
});

const audioFile = fs.createReadStream("./audio.mp3");

const transcription = await client.audio.transcriptions.create({
  file: audioFile,
  model: "openai/whisper-large-v3",
});

console.log(transcription.text);

​
Transcription with Language Specification

Improve accuracy by specifying the language: 
const transcription = await client.audio.transcriptions.create({
  file: audioFile,
  model: "openai/whisper-large-v3",
  language: "en",
});

console.log(transcription.text);

​
Transcription with Timestamps

Get word-level or segment-level timestamps: 
const transcription = await client.audio.transcriptions.create({
  file: audioFile,
  model: "openai/whisper-large-v3",
  language: "en",
  response_format: "verbose_json",
  timestamp_granularities: ["word", "segment"],
});

console.log(transcription);

​
Transcription with Custom Prompt

Provide context to improve accuracy: 
const transcription = await client.audio.transcriptions.create({
  file: audioFile,
  model: "openai/whisper-large-v3",
  prompt: "This is a medical consultation discussing patient symptoms and treatment options.",
});

console.log(transcription.text);