Step 1
Pick or build a voice
Choose from built-in voice presets, clone yourself or a reference sample, or generate a brand-new voice. Cloned voices stay on your disk, they never touch a server.
For Audiobook & Podcast Producers
No Per-Character Billing. Ever.
Demodokos Foundry runs AI narration locally on your GPU. Full-length books, multi-speaker dialogue, 36+ emotional voice styles. One flat subscription. Nothing uploaded. Nothing metered.
36+ Voice Styles Multi-Speaker Dialogue Voice Cloning 10 Languages
Signed Installer Defender Verified Generation runs locally
Cost, privacy, multi-speaker workflow, and a revision that charges you twice for getting it right.
An 80,000-word novel is roughly 400,000 characters. At ElevenLabs’ Scale tier that’s a significant chunk of your monthly quota on a single project, before a single edit. Add revisions, alternate takes, and character voice tests, and you’re burning through credits on work that might not even make the final cut.
Your unpublished book. Your podcast scripts. Your character voice samples. All uploaded, processed, and stored on infrastructure you don’t control, under terms of service written to protect them, not you. For finished, published work, maybe that’s fine. For unreleased material, that’s a risk most producers don’t think about until it’s too late.
A scene with four characters means four separate voice sessions, four separate exports, and hours of manual stitching in a third-party editor just to get the pacing right. There’s no shared timeline. No way to hear all the voices together until you’ve already exported each one individually and assembled them yourself.
Your editor flags a chapter. A character’s delivery felt flat. You rework three pages. Every single regeneration costs the same credits as the original pass. Cloud tools don’t distinguish between “first attempt” and “making it better.” The result: producers start settling for “good enough” instead of “right,” because right costs too much.
Demodokos Foundry runs on your GPU. Narrate one chapter or a hundred, the price doesn’t change and your files never leave your desk.
Your manuscript stays on your computer. Your voice samples stay on your computer. Your finished audio stays on your computer. Foundry runs entirely on your GPU. No uploads, no cloud processing, no servers holding your unreleased work.
A thriller narrator at intensity 4 sounds nothing like a memoir narrator at intensity 2. Pick the genre, set the tone, and the delivery matches. 10 languages supported natively, so international editions come from the same workflow.
Assign a different voice to each character and generate the full scene together. Everyone’s on the same timeline, with the same pacing, in one project. No separate exports. No stitching in a third-party editor.
Clone a narrator voice from a short audio clip and use it across the entire book. Same tone, same character, chapter after chapter. Built-in stem separation means you can pull clean voice from existing recordings, even if they have background music.
Arrange chapters, adjust levels, add room tone, apply spatial treatment that makes narration feel warm instead of flat. Everything from trimming silence to final export happens inside Foundry. One tool, one window, one workflow.
Generate original intro and outro tracks, background ambiance, and chapter transitions without opening a second tool. Podcast producers get full episode production in one place. Audiobook producers get polished, publish-ready files.
Cancel anytime. No credits. No limits.
No studio booking. No per-character fees. The entire pipeline, voice and music, runs on your Windows machine in under a minute per page.
First time here? Watch the 4-minute install and first-launch tutorial before you start.Choose from built-in voice presets, clone yourself or a reference sample, or generate a brand-new voice. Cloned voices stay on your disk, they never touch a server.
Drop in a chapter, a full book, a video outline, or a dialogue file. The redesigned script editor splits it into lines the moment you paste, so you can hand each character its own voice and direct a whole cast, not just a single narrator.
Tag any paragraph as calm, excited, whispered, angry, sarcastic, or anything in between, with 5 intensity levels per emotion. The voice stays the same character; the feeling changes.
Original scores, ambient loops, full songs with vocals, instrumental beds. Any genre, any mood, sung in any of 50 languages. Score your narration or write a standalone track, then drag it straight onto your timeline. No second tool, no separate subscription.
Drop studio-grade effects on a single line or the whole track. Turn a narrator into an alien, a demon, or a vintage radio broadcast in one click, then reach for reverb, EQ, auto-tune, formant shifting and glitch, all non-destructive. A full DSP rack, built in, no plugins and no external DAW.
Foundry runs on Windows with an NVIDIA GPU. Here's a quick overview.
Windows 10 or 11, 64-bit
Optimized for Windows workstations
SSD/NVME disk recommended
NVIDIA GPU with 6 GB+ VRAM
any RTX series card, incl. GTX 1080, 12 GB+ recommended
6 to 8 GB: reduced performance
16 GB+: + multilingual Creative AI
24 GB+: + brilliant Creative AI
32 GB+: + extreme performance
Setup: 70 MB
Latest app version: v2.2.34
First-run model pack: ~20 to 25 GB
More model packs available later
Narrate your manuscript on your own machine. One flat subscription, no per-character fees, your files never leave your desk.
Cancel anytime · Runs 100% local · Windows desktop app