​
Overview

The Text to Speech API converts written text into natural-sounding speech output. You can use predefined speaker accents or clone a voice from an audio sample to create personalized speech output.

  • Support for multiple languages and accents
  • Voice cloning from audio samples
  • High-quality, natural-sounding output
  • Simple integration options

​
API Endpoint

POST /v1/ai/tts

​
Quick Start

Javascript
import { JigsawStack } from "jigsawstack";

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

const response = await jigsaw.audio.text_to_speech({
  text: "Hello, how are you doing?",
  accent: "en-US-female-27",
});

const data = await response.blob();

See Speaker Voice Accents for the complete list of supported speaker voice accents.

​
Response

The API returns the generated audio file directly in the response body as binary data, typically in MP3 format.

​
Using Text to Speech Effectively

  • Keep text natural: Write text that sounds natural when spoken aloud
  • Consider punctuation: Use commas and periods to create natural pauses
  • Test different accents: Try different voice options to find the best fit for your use case
  • For voice cloning: Use high-quality audio samples with minimal background noise

​
Examples

Using Speaker Clone URL
import { JigsawStack } from "jigsawstack";

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

const response = await jigsaw.audio.text_to_speech({
  text: "Hello, how are you doing?",
  speaker_clone_url: "https://example.com/path/to/voice-sample.mp3",
});

const data = await response.blob();
Using File Store Key
import { JigsawStack } from "jigsawstack";
import fs from "fs";

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

// Read the audio file
const audioFile = fs.readFileSync("./speaker.wav");

// Upload the file
const uploadResult = await jigsaw.store.upload(audioFile, {
  filename: "speaker",
});

// Retrieve the file key
const fileKey = uploadResult.key;

// Use the file key for Text to Speech
const response = await jigsaw.audio.text_to_speech({
  text: "Hello, how are you doing?",
  speaker_clone_file_store_key: fileKey,
});

const data = await response.blob();

Was this page helpful?

Suggest editsRaise issue