Audio at the speed of your content
Generate narration for every new article, lesson, or product page automatically the moment it goes live.
Send text and get natural speech back. The Voiceslab TTS API brings our studio voices—including your own cloned voices—to your app with one simple REST call and transparent per-character pricing.

Text to speech API
Voiceover workflow
Script to voiceover
Preview, refine, export
WORKING VOICE DEMO
The API uses the exact same voices and engine as this demo. Type a sentence, pick a voice, and listen before writing a single line of code.
WHAT IT IS
A text to speech API lets your software convert written text into spoken audio automatically. Instead of opening a studio and clicking generate, your app sends an HTTP request and receives an audio file ready to play, store, or publish.
The Voiceslab API is a REST API with endpoints for single-voice speech, multi-speaker dialogue, available voices, and your credit balance. It works with any programming language that can make HTTP requests and draws from the same credit balance as your Voiceslab plan.
ONE REQUEST
Authenticate with your API key, send your text and a voice ID, and save the audio. Add ?response=json to return a download link instead of the audio file.
Read the API documentationcurl https://voiceslab.io/api/v1/tts \
-H "Authorization: Bearer $VOICESLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{"text": "Welcome to our app!", "voice_id": "Rachel"}' \
--output welcome.mp3WHY TEAMS USE IT
When audio is core to your product, generating files by hand doesn't scale.
Generate narration for every new article, lesson, or product page automatically the moment it goes live.
Clone a voice once in the studio, then call it through the API so every audio clip keeps a consistent, recognizable sound.
Skip hosting speech models and managing GPUs. Send text, get audio back, and pay only for the characters you convert.
HOW IT WORKS
Most developers make their first successful request within minutes.
API speech generation is available on every paid plan and also works with credit packs.
Open Dashboard → API & MCP, name your key, and optionally set a daily character limit.
Call the voices endpoint to list library voices and your cloned voices, then copy a voice ID.
Send your text and voice ID to the speech endpoint and save the returned MP3, WAV, or Opus file.
WHAT YOU GET
Everything you need to integrate natural speech into an app, workflow, or content pipeline.
Use voices from the Voiceslab library or voices you've cloned in the studio. Cloned voices remain private to your account.
Convert a full article or script in a single call and receive the output as MP3, WAV, or Opus.
Turn a script with up to 5 voices into a single MP3 conversation for podcasts, lessons, and tutorials.
Adjust speaking speed and volume per request without changing the underlying voice.
Include an Idempotency-Key so retried requests return the original result without charging you twice. Failed generations are never billed.
Create up to 5 API keys, cap each with an optional daily character limit, and track daily usage in your dashboard.

Direct the delivery
Turn a script with up to 5 voices into a single MP3 conversation for podcasts, lessons, and tutorials.

Build for more audiences
Include an Idempotency-Key so retried requests return the original result without charging you twice. Failed generations are never billed.
PRICING AND LIMITS
The API shares the same credit pool as the Voiceslab studio: 1 credit equals 1 character of input text across every language. Monthly plan credits are used first, followed by credit-pack credits, which never expire.
Basic includes 200,000 credits per month and Pro includes 500,000 credits per month. Each API key can make up to 60 requests per minute, and each account can run 2 generations at the same time. Generated audio is stored for 7 days, and JSON download links remain valid for 1 hour.
QUESTIONS BEFORE YOU CREATE
API requests use your Voiceslab credits at 1 credit per character of input text in every language. Basic includes 200,000 credits per month, Pro includes 500,000 credits per month, and credit packs provide extra credits that never expire.
Free accounts can create API keys, list voices, and check their credit balance, but generating speech requires a paid plan or a credit pack.
Yes. Clone your voice in the Voiceslab studio, then pass its voice ID in your API requests. Your cloned voices are private and can only be used by your account.
Single-voice speech supports MP3, WAV, and Opus. Multi-speaker dialogue is returned as MP3 only.
No. If a generation fails, credits are refunded automatically. When you send an Idempotency-Key, retries of a completed request are not charged again.
Yes. The Voiceslab MCP server lets Claude, ChatGPT, Cursor, and other MCP clients list voices and generate speech using your account.
Create an API key, pick a voice, and make your first request in minutes.
Get Your API KeyText to speech API
Voice track