Speech to Text

​

Overview

Transform audio and video files into accurate text transcriptions using our powerful Speech to Text API. Built on Whisper large V3, this service provides:

• High-accuracy transcription across multiple languages
• Speaker identification for multi-person conversations
• Translation capabilities for global content
• Asynchronous processing via webhooks

​

Supported Formats and Limitations

• Supported formats: MP3, WAV, M4A, FLAC, AAC, OGG, WEBM
• Maximum file size: 500MB
• Maximum audio duration: 4 hours

​

Request Parameters

​

Body

​

Header

​

Response Structure

​

Direct Response

​

Webhook Response

When using webhook_url, the initial response will be different:

The complete transcription result will later be sent to your webhook URL with the same structure as the direct response.

​

Advanced Features

​

Speaker Diarization

Speaker diarization is the process of separating an audio stream into segments according to the identity of each speaker. When you enable the by_speaker parameter, the API will:

1. Transcribe the audio as usual
2. Identify distinct speakers in the recording
3. Label each segment with a speaker identifier (e.g., “SPEAKER_1”, “SPEAKER_2”)
4. Return both the standard chunks and a separate speakers array with speaker-separated transcriptions

This is particularly useful for:

• Meeting transcriptions
• Interview transcriptions
• Podcast transcriptions
• Any multi-speaker audio content

​

Webhook Usage

For long audio files, processing might take some time. Instead of keeping the connection open and waiting for the result, you can provide a webhook_url parameter. The API will:

1. Return immediately with a job ID
2. Process the audio asynchronously
3. Send the complete transcription results to your webhook URL when finished

Make sure your webhook endpoint is set up to:

• Accept POST requests
• Parse JSON content
• Handle the same response format as the standard API response

import { JigsawStack } from "jigsawstack";

const jigsawstack = JigsawStack({
  apiKey: "your-api-key",
});

// Basic transcription
const result = await jigsawstack.audio.speech_to_text({
  url: "https://example.com/path/to/audio.mp4",
});

// With speaker diarization
const resultWithSpeakers = await jigsawstack.audio.speech_to_text({
  url: "https://example.com/path/to/audio.mp4",
  by_speaker: true,
});

// With a webhook for asynchronous processing
const asyncResult = await jigsawstack.audio.speech_to_text({
  url: "https://example.com/path/to/audio.mp4",
  webhook_url: "https://your-server.com/webhooks/transcription",
});

// Translating to English
const translationResult = await jigsawstack.audio.speech_to_text({
  url: "https://example.com/path/to/audio.mp4",
  translate: true,
});

// Using a specific language
const specificLanguageResult = await jigsawstack.audio.speech_to_text({
  url: "https://example.com/path/to/audio.mp4",
  language: "es-ES", // Spanish
});

// Using a file from storage
const fileStoreResult = await jigsawstack.audio.speech_to_text({
  file_store_key: "uploads/recording.mp3",
});

{
  "success": true,
  "text": "Hey guys, I'm pretty excited to talk about a new API that we're going to be releasing in Jigsaw Stack...",
  "chunks": [
    {
      "timestamp": [0.96, 7.2],
      "text": "Hey guys, I'm pretty excited to talk about a new API that we're going to be releasing in Jigsaw"
    },
    {
      "timestamp": [7.2, 14.56],
      "text": "Stack. It's our AI Scrape API, which can basically scrape any website by just prompting and giving"
    }
    // Additional chunks...
  ]
}