Developer quickstart

Generate speech with the Python or TypeScript SDK.

Official packages: Python on PyPI and TypeScript on npm.

Create a key in the VoiceLab app with TTS Access and Voices Read, then export it:

export VOICELAB_API_KEY=your_api_key

Choose a language

Choose your language

Generate your first audio file

1. Install the npm package

   Terminal

   npm install @voicelab/sdk

2. Generate speech

   TypeScript

   import { writeFile } from "node:fs/promises";
   import { VoiceLab } from "@voicelab/sdk";
   
   const voiceLab = new VoiceLab({
     apiKey: process.env.VOICELAB_API_KEY!,
   });
   
   const speech = await voiceLab.tts.synthesize({
     text: "Hello from VoiceLab.",
     language: "en",
     voiceId: "voice_01J9NEUTRAL0000000000000001",
   });
   
   await writeFile("speech.wav", new Uint8Array(speech.audio));

1. Install the pip package

   Terminal

   pip install voicelab-sdk

2. Generate speech

   Python

   import os
   from voicelab import VoiceLab
   
   client = VoiceLab(api_key=os.environ["VOICELAB_API_KEY"])
   
   speech = client.tts.synthesize(
       text="Hello from VoiceLab.",
       language="en",
       voice_id="voice_01J9NEUTRAL0000000000000001",
   )
   
   with open("speech.wav", "wb") as audio_file:
       audio_file.write(speech.audio)

Choose a voice_... ID from the voice catalog for your account. Use the HTTP reference for operations your SDK version does not expose.

Next

• For AI agents

• Authentication

• TTS HTTP reference

• STT HTTP reference