Introducing Song Creator Pro — create music with AI, locally on your device. Coming soon →

Roadmap

Building the Future of Voice

From concept to reality — our journey to create the most powerful local voice generation tool.

Done

Intel Arc & AMD Support (Experimental)

Experimental support for Intel Arc and AMD GPUs. Run voice generation on a wider range of hardware beyond NVIDIA.

February 2026

Done

Streaming Audio via API

Real-time audio streaming through the API for low-latency integrations. Generate and receive audio chunks as they're produced.

March 2026

Done

Full App Internationalization

The entire app interface translated into English, Chinese, Japanese, Korean, German, French, Spanish, Russian, Portuguese, and Italian. Use Voice Creator Pro in your preferred language.

March 2026

Done

Expanded Language Support — Portuguese & Italian

Portuguese and Italian have been added to the voice generation engine, bringing natural-sounding speech to even more users worldwide.

March 2026

Done

Remote Web Interface

Access Voice Creator Pro from any device on your network. The app runs locally on your desktop while you control it from your phone, tablet, or another computer.

March 2026

Done

macOS Support

Voice Creator Pro is now available on the Mac App Store. Full feature parity with the Windows version, optimized for Apple Silicon.

March 2026

Soon

Expanded Language Support

Adding 13 new languages to the voice generation engine: Arabic, Danish, Greek, Finnish, Hebrew, Hindi, Malay, Dutch, Norwegian, Polish, Swedish, Swahili, and Turkish. Broadening global reach with natural-sounding speech across more regions and cultures.

Soon

Expanded Voice Library

A larger collection of ready-to-use voices across different ages, accents, and styles — so you can find the perfect voice.

Soon

Generation Queue

Batch multiple scripts and process them one after another. Queue up your work and let Voice Creator Pro handle the rest while you focus on other tasks.

Planned

Quantized Model Support

Run voice generation on systems with limited VRAM using optimized quantized models. Lower hardware requirements without sacrificing quality.

Planned

More Voice Models

Choose from a wider selection of TTS models with different characteristics — varying in speed, quality, and style to match your specific use case.

Planned

Voice Design Templates

Pre-built prompt templates for crafting custom voices. Quickly design voices — no prompt engineering needed.

Planned

Long-Form Content Studio

A dedicated interface for generating long-form audio. Automatically splits text into chunks, generates each segment, and merges them into a single seamless file.

Have an idea that should be on our roadmap?

Suggest a Feature
Stay in the loop

Get Updates

Get notified about new features, platform launches, and updates. No spam, unsubscribe anytime.

No spam, ever. Unsubscribe anytime.