About This Software

Change your voice in real time

Simple Voice Changer turns your microphone into someone else, live, in Discord, Steam voice chat, OBS, Zoom and any game that lets you pick a microphone. Choose a realistic neural voice or a classic effect, fine-tune it with over thirty knobs, and play sound clips, music or another app's sound into the call while you talk. It all runs on the PC you already have: no account, no cloud and no subscription, and everything except the optional Character Voices runs without a graphics card.

Neural voices on your CPU

Pick a neural voice and a small neural network (Beatrice 2) turns your voice into one of 200 human voices, men and women, as you speak. It is the easy way to sound more feminine or more masculine. It runs on your processor, offline. Pick a voice, press Match my pitch, and add any effect on top. The app shows how much CPU it uses and how much delay it adds: on our test machines that was 20 to 31% of one CPU core and about 75 to 85 ms. A Lower CPU use option is there for older PCs. While it is on, your real voice is never sent.

Character Voices: bring your own RVC voice model

Have an RVC voice model of a character? Load its .pth file, or the .zip you downloaded, and talk through it live, with every effect still on top. Tell it how high the character's voice is and Auto pitch sets the rest; an .index file that came with the model makes it sound closer. No voice models are included and the app does not download any: you find them yourself, and results vary depending on the model. A gaming graphics card is recommended (any brand); a fast processor can run it with more delay. Expect about 0.3 seconds of delay on a graphics card and about half a second on a processor, which people on a call will notice. Test my computer tells you in a few seconds whether your PC can run it. Model files are opened safely: the app reads only the voice data and never runs anything inside them. Use only voices you have the right to use.

What to expect

The neural voices are anonymous audiobook readers, not copies of famous people. They give you a believable other voice, while your words, timing, accent and expression stay yours. The app comes with no copies of real people or characters. If you load an RVC voice model you found yourself, you sound like that model, as good as the model is, and what you do with it is up to you and the law where you live. Even then a character is partly acting: the model changes the sound of your voice, not the way you speak. The classic effects are effects: a robot sounds like a robot. Changing a voice takes a moment, so your voice runs a fraction of a second behind. The screenshots and the trailer show the app exactly as it is.

Works with Discord, checked for you

Turn it on and your PC gets a new microphone: "CABLE Output" on Windows (the free VB-CABLE driver, installed with the app) or "Simple Voice Changer Mic" on SteamOS and Linux (no driver needed). Pick it in Discord, OBS, Zoom, Steam voice chat or your game. The Setup page checks that your changed voice really arrives, walks you through Discord's own settings and shows, live, when Discord is hearing you. If a voice ever cuts out, turn off noise suppression in that app and use the built-in Noise Removal instead.

Ten classic effects and 30+ knobs

Deep Voice, Chipmunk, Robot, Cave Echo, Megaphone, Monster, Radio, Demon, Vocoder Bot and 8-Bit, ready to use or to start from.

• Voice: pitch, formant, breath, melody, autotune

• Character: robot, vocoder, distortion, bitcrush

• Texture and motion: whisper, growl, tremor, flanger, phaser, auto-wah

• Space and tone: echo, reverb, bass, mid, presence, treble

• Clean-up: noise gate, low cut, high cut

• Layers: extra pitched copies for demons, harmonies and choirs

Every knob works instantly. The Voice page shows only the few that matter for the voice you picked; one switch shows them all. Save your own voices, give each one a hotkey, or press Randomize for something new.

Soundboard, music and App to Mic

• Soundboard: your own clips, up to 90 seconds each, on as many boards as you like. Every sound can have its own global hotkey, up to eight play at once, and your voice keeps working over them.

• Instant replay: turn it on and the app keeps the last 30 seconds of what you hear. When something funny happens, one key saves it as a new sound.

• Background music: play a queue of tracks into the call. It ducks under your voice automatically and is never pitch-shifted. Give any song its own hotkey for your intro or be right back music, or play it only on your speakers so OBS can take it as its own source.

• App to Mic: send another app's sound into your mic, with a hotkey to switch it on and off: Spotify, a browser, or your Discord friends, so they can join a dubbing game they don't own.

For your recordings

Voice to File puts your voice on recordings you already have, for videos and voice-overs, and saves new files next to the originals. It can also move them towards the voice of a short clip you choose, using another small neural network on your CPU: a likeness for recordings, not live, and not a perfect copy. Only use voices you have permission to use.

Hear what they hear

Record six seconds of your own voice once, and every voice gets a play button that plays you through it, so you hear the result before anyone on the call does. The Setup page records what actually arrives at the virtual mic, exactly what Discord receives. You can also hear yourself live in your headphones.

A cleaner mic, built in

Mic Boost, Noise Removal, Auto Volume and Anti Cut-off tidy up your microphone before any effect runs, so fans, hum and keyboard clatter stay out of the call and the ends of your words don't get clipped.

Hotkeys that work in-game

Turn the effect on or off, mute, push to talk, switch voices, fire sounds, start a song or send an app into your mic without leaving your game. On Windows (and Linux on X11) a key still fires while you hold Shift or Ctrl to sprint or crouch, and push to talk leaves its key to the game. F1 to F12 can be hotkeys too, for a Stream Deck or macro pad, and if another program already uses a key, the app tells you. On SteamOS and other KDE or GNOME desktops, the desktop asks you once to confirm new shortcuts. You can also run it from a Stream Deck, Streamer.bot, Touch Portal or your phone with the built-in remote control.

Private, native and yours

No account and no internet connection needed: your voice and your clips never leave your computer. Native builds for Windows and SteamOS/Linux (no Proton), in English, German, Spanish, Portuguese, Russian, Ukrainian and Chinese. Pay once: no subscription, no DLC voices, nothing to unlock.

AI Generated Content Disclosure

The developers describe how their game uses AI Generated Content like this:

Optional AI voice features run locally on your PC and only change the sound of your own voice: Neural voice (200 anonymous voices), Character Voices (RVC voice models you supply yourself; none are included) and Voice to File's clip voice. Nothing is uploaded.

Name of AI model included with the game: Beatrice 2 (Neural voice), RVC voice conversion with user-supplied models (Character Voices), SPARC (Voice to File's clip voice). All run locally; no online service.