From natural AI voices to professional mastering, all running locally on your machine.
From audiobook narrators to podcast hosts, game characters, app assistants, and explainers. Preview any voice instantly. Pro users can design new Omni voices from selected attributes.
Speech generation, editing, and mastering run on your desktop. Your scripts and audio are not uploaded for processing. Internet access is still required for setup, model downloads, activation, and periodic license validation.
Record yourself or use a voice you have permission to clone. Vois creates the custom voice on your device, ready for every approved script.
Use Omni to build a voice from gender, age, pitch, accent, and style. No audio sample required. Preview, refine, then save it as a reusable voice.
Tag speakers in one script, assign a voice to each, and generate the entire conversation in one pass.
One-click presets hit the loudness target for ACX audiobooks, Spotify, Apple Podcasts, and YouTube. LUFS normalization, de-essing, and limiting are built in.
Custom pronunciation rules for names, brands, acronyms, and technical terms. Import a glossary by CSV and apply it across every project.
Omni on Pro lets every voice speak 600+ languages, from major world languages to regional dialects. The multilingual engine covers 23 languages on any plan. Switch languages mid-project without switching voices.
Control Vois from the command line. Let Claude Code, Claude Desktop, ChatGPT Desktop, Codex, Cursor, or Gemini orchestrate your voice workflows using hosted skill files.
Start creating voice content in 600+ languages with unlimited generation.
