API Overview

Coming in 2027

The VocalLab API is currently in development and planned for release in early 2027. It will allow developers to integrate VocalLab's voice generation directly into their own applications.

Planned capabilities

• Text-to-speech — generate audio from text via HTTP requests
• Voice listing — query available voices with filters (language, gender, style)
• Voice cloning — submit audio samples and create custom voice models
• Async generation — webhook callbacks for long audio jobs
• Streaming — real-time audio streaming for latency-sensitive use cases

Who it's for

• Developers building apps with voice features
• Companies needing bulk generation pipelines
• SaaS products wanting to embed VocalLab's voices

Pricing

API usage will be billed separately from subscription plans, likely on a per-minute or per-character model. Details will be announced closer to launch.

Stay updated

To be notified when the API launches, contact us with "API interest" in your message, or follow our blog for announcements.

Current alternative

While the public API is not yet available, Pro and Studio plan subscribers can use the web app and Studio editor for production workflows. Enterprise customers can contact us to discuss custom integration options.