Text-to-Speech API

Our low-latency API can be used for chat applications, to narrate a blog post, to create voice-overs for videos, and much more. The API is the most affordable on the market. Save up to 90% compared to other providers, like Elevenlabs or OpenAI.

Voices

We offer 6 unique voices to choose from. Only English is supported at the moment. More languages will be added soon.

API Usage

Our OpenAI compatible API makes it easy to switch. If you haven't already, you will need to create an API key to authenticate your requests.

import { createWriteStream } from "fs";
import { Readable } from "stream";
import { finished } from "stream/promises";

const response = await fetch("https://api.lemonfox.ai/v1/audio/speech", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
  },
  body: JSON.stringify({
    input: "Artificial intelligence is the intelligence of machines or software, as opposed to the intelligence of humans or animals.",
    voice: "leo",
    response_format: "mp3"
  })
})
const fileStream = createWriteStream("speech.mp3", { flags: "wx" });
await finished(Readable.fromWeb(response.body).pipe(fileStream));

API Response

The API returns the audio file content. You can specify the format of the audio file with the response_format parameter.

API Parameters

The API POST https://api.lemonfox.ai/v1/audio/speech takes the following parameters: