Hey Sumo-lings, I'm Praney, the founder of Vois Studio.
I'm mildly dyslexic, and text-to-speech has been part of my workflow for years. As I started producing more voiceovers, tutorials and audiobooks, the usage bills grew too. One YouTube channel became ten, with a video going out on each channel every day.
What really frustrated me was paying again for every revision. Change a few words, adjust the delivery, try another take, and it cost more money. I wanted the freedom to keep working on a piece until it sounded right, without every attempt adding to the bill.
That's why I kept building my desktop app into Vois Studio: a place to take a script through to finished audio, rather than stopping at a generated voice clip.
You can work with multiple speakers, generate speech on your computer after installing the required models, arrange clips with music and sound effects, master the mix, and export. Vois runs on Apple Silicon Macs and Windows x64.
Our early community is using it for audiobooks, podcasts, tutorials, courses and game narration. For those working with AI agents, the Vois CLI lets a local-capable agent handle repeatable production steps while you stay in control. CLI access is included in AppSumo Tiers 2 and 3; commercial use is included in Tier 3.
Over the last six months, I've released 18 updates to Vois, steadily adding capabilities and refining the experience. Your real projects help me understand what to work on next, so tell me what you want to make and where you get stuck.
If you've just activated, start with one short script and one voice before moving into a larger project. If you need help, join the Vois Discord at https://discord.gg/7e7fnE55Nh, or email [email protected]. I'm based in Australia, so time zones can affect when you hear back.
Thanks for taking a look. I'm looking forward to seeing what you create.