For Indie Game Developers
No Voice Acting Budget.
Local AI voice generation built for indie devs who need a full cast, not a casting bill.
36+ Character Voice Styles Voice Cloning Batch CLI Generation Runs Locally — No Cloud
Signed Installer Defender Verified Generation runs locally
You built the game. Now you need a cast.
You're building something real. The gameplay is there. The world is there. And then you hit the voice problem.
You need guards that sound different from merchants. Villains with weight. Quest givers who don't all sound like the same bored narrator. You price out a session and reality hits fast.
Finding the right voices, directing sessions, handling revisions — that's a production pipeline most indie studios can't run while also shipping a game.
So you ship with text-only dialogue or TTS that sounds robotic. Your trailer feels cheaper than the game deserves.
Per-line cloud pricing that scales with your dialogue count, and your scripts sitting on someone else's servers under terms you probably didn't read all the way through.
What if you could cast every voice yourself?
Everything your cast needs. Nothing it doesn’t.
Ages, genders and character archetypes, each voice carries the full emotional range. Happy, sad, dramatic, tense, sarcastic, drunken, even singing, with 5 intensity levels per emotion. The voice stays the same character; the feeling changes.
Record yourself doing a character voice, clone it, and use it consistently across 200 lines without a single session booking. Or clone from any reference audio with stem separation built in.
Feed it a script file, get audio files back. No clicking through a GUI for every single line. Script in, audio out. Integrates with your existing build pipeline.
Arrange, trim and mix dialogue, music and ambience on a single multi-track timeline. Cue lines to picture, layer SFX, balance levels, export engine-ready files. No separate DAW required.
Turn a clean read into a goblin in a cave, a captain on a radio, a demon mid-roar. Tavern reverb, telephone filter, underwater, pitch and formant shift, distortion, spatial audio. Stack freely, non-destructive, one click.
Generate original background scores, ambient loops, combat tracks and tavern music directly inside Foundry. Any genre. Unlimited. No separate subscription.
No credits. No per-asset fees. Generate a thousand lines today and a thousand more tomorrow for the same flat price. The math stays simple no matter how big your game gets.
No studio booking, no per-line fees. The entire pipeline runs on your Windows machine in under a minute per page of dialogue.
First time here? Watch the 4-minute install & first-launch tutorial before you start.Pick from built-in voice presets, clone yourself doing a character voice, or generate a brand new one. Cloned voices stay on your disk. They never touch a server.
Paste a chapter of NPC lines, a CSV from your localization tool, or feed the whole file through the CLI. No character limit, no per-line counting.
Assign emotion and intensity per line. A guard barks at intensity 5, whispers a warning at intensity 1, same voice, same character. Tune until it lands.
Generate combat tracks, tavern beds and ambient loops directly in Foundry. Drop them on the timeline under your dialogue. No second tool, no separate subscription.
Render WAV, MP3 or FLAC locally and drop straight into Unity, Unreal, Godot, FMOD or Wwise. Re-run the batch when a line changes, only the diffs get regenerated.
64-bit required
6 GB+ VRAM · GTX 1080 or better
12 GB+ recommended for full-speed batch
Login once at startup — everything else is local