A local AI audio studio for music, speech, editing, and automation.
Demodokos Foundry is a Windows desktop app that lets you generate music and speech, separate stems, patch sections, mix on a timeline, and export finished audio - all on your own machine.
100% Local Generation Windows 6GB+ VRAM Create without cloud credits 50 music / 10 speech languages
Signed Installer Defender Verified Generation runs locally
Music, voices, audiobooks, narration - all from a simple text description.
Everything you heard above was created inside Foundry - from songs to narration to multi-voice scenes.
Most voice tools read words one at a time. Demodokos Foundry v4 is built on acoustic-token synthesis: a language transformer takes in the whole sentence first, modelling context, intent and delivery instead of pronouncing words in isolation. The voice is then generated from fine-grained acoustic tokens, roughly one decision every 40-80 milliseconds, which is what gives it control over timing, emphasis, rhythm, emotion and pacing down to the smallest beat.
A full hour of finished speech in under five minutes on an RTX 5090. And all of it consistent in the correct emotions and voices.
Each cloned or synthetic voice is grounded in learned neural representations that capture identity, timbre, accent and vocal texture, with no hundreds of hours of fine-tuning. As it generates, identity-preserving latent conditioning and spectrogram-based consistency control keep every line locked to the same speaker.
On top of that identity sits an independent performance layer: more than 40 emotions and speaking styles, each in five intensity levels, on generated and cloned voices alike. Emotion, rhythm, pacing, accent and texture can change completely while the person underneath never does.
Choose a character and tap through their emotions. It is always the same voice, just performing in a completely different way.
Most cloud tools make you use separate products for music, voice, editing, and automation. Foundry brings it all together in one local studio.
Music creation, expressive speech, real mixing, and automation.
No cloud credits burning through your budget. Your hardware, your rules, your pace.
Varied, stable, and recognizable across styles and scenes.
Fast long-form generation, including music tracks up to 10 minutes.
Timeline editing, stem separation, patching, cover/extend workflows, and pro DSP.
Helps analyze, segment, refine, direct, and create.
30+ emotions, multiple intensities, and consistent voice identity.
Batch workflows, agentic control, and serious automation.
This is not another generator. It is a complete local AI audio production environment.
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 YouTube outline, a sales page, or a dialogue file. No character limit, no word counter watching you.
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. Drag the track straight onto your timeline. No second tool, no separate subscription.
Render the final WAV, MP3 or FLAC locally, then drop it straight into your DAW, video editor, audiobook submission, game engine or podcast feed.
Generate music in 50 languages and speech in 10.
Describe a song, a voice-over, or a narration. Foundry generates complete audio with vocals, instruments, or spoken word, ready in seconds, entirely on your machine.
Type what you imagine: music or speech. Adjust mood, tempo, voice style, press Generate. A full track or spoken read, done in seconds.
Turn scripts, chapters, and show segments into polished spoken audio. Multi-speaker scenes with distinct voices, emotional direction, and 15× real-time generation speed.
Assign voices to roles, steer emotion per line, and produce full audiobook chapters or podcast episodes without a recording session.
Layer narration over original scores, blend dialogue with sound design, and mix spoken word with music beds, all in the same editor. Build trailers, immersive stories, and rich audio productions without switching apps.
Drag voice, music, and effects onto the same visual tracks. The spectrum analyzer identifies BPM, time signature, and key. Mix everything, then export your finished production.
A narrator who breaks with sadness at just the right moment. A villain whose calm whisper turns to fury. A podcast host who sounds genuinely thrilled. With 40 emotions and 5 intensity levels, every cloned or preset voice stays perfectly in character.
Pick any emotion, from whisper and rage to heartbreak and storytelling, then dial the intensity. Assign different moods per line or paragraph. 60 speaker presets, voice cloning, and it all sounds like the same person. Not a robot.
Take any song apart: vocals, drums, guitar, piano. Each clean on its own track. Use Karaoke mode and mix in your own vocals or an AI-generated track.
Splits any song into up to 7 separate tracks. Each instrument and voice gets its own channel.
Something sounds off? Select just that area, generate a patch in seconds, and DSP-blend it seamlessly. Everything else stays exactly as it is.
Select any region and regenerate just that section. Before and after stay untouched. Spectral blending ensures seamless boundaries.
Feed Foundry any audio and restyle it completely, or extend a 30-second idea into a full song. Same structure, with an entirely new character or a seamless continuation.
Load audio as a foundation and apply a new style with Cover mode. Or select any part and press Extend to continue naturally from where it left off.
EQ, reverb, chorus, tape warmth, voice transformation, and glitch, with 200+ presets across 7 groups. Stack freely on your timeline, non-destructive, one click.
From surgical 24-band EQ to cathedral reverb, from drum punch to spectral crossfading. Auto-Tune, voice effects, glitch, and granular stretch, all non-destructive.
120+ commands to generate, compose, separate stems, mix, and export. Build pipelines, batch-produce content, or let an AI agent drive Foundry for you.
120+ commands. Create, compose with Creative AI, manage tracks, split stems, export. Build anything.
Start with a 7-day free trial, then pick the plan that fits. Everything runs on your computer - no cloud, no queues, no per-song limits.
For your own projects - YouTube, games, podcasts, personal work
For 1 person - use it for your own content, not for client work
Do work for clients - freelance, agency, studio
1 seat per person - produce work for your clients
For teams of 5 or more
Required for 5+ seats, 10+ employees, or $2M+ revenue
Everything runs on your computer. Private, fast, no cloud queues.
Cancel anytime, no further charges. Start with the free trial - full access, pay only if you love it.
Foundry runs on Windows GPUs, with full support on NVIDIA and limited support on AMD. Here's a quick overview.
Windows 10 or 11, 64-bit
Optimized for Windows workstations
SSD/NVME disk recommended
NVIDIA GPU with 4 GB+ VRAM
any RTX series card, incl. GTX 1080, 12 GB+ recommended
AMD GPU with 8 GB+ VRAM
Full Music and Speech quality since v2.1
up to 6 GB
reduced quality
6 to 8 GB
reduced performance
16 GB+
+ multilingual Creative AI
24 GB+
+ brilliant Creative AI
Setup: 70 MB
Latest app version: v2.1.23
First-run model pack: ~20 to 25 GB
Download Demodokos Foundry setup here.
A5589A6DAF1B879BC773D62F0E2A19E2D4F3DE369AAF88FE319DF0DEF525CC95
Windows release available now
A faster, lighter, smarter generation engine.
Foundry 2.1 brings our native Foundry Music v4 engine, improved models and downloads, broader GPU support, and a smoother production experience.
The foundation for a broader local audio platform.
Foundry 2.0 introduced the native Speech v4 stack, a refreshed voice library, expanded GPU support, and a major interface and workflow overhaul.
Version 2.1 introduces our native Foundry Music v4 engine and improved models, much faster downloads, broader GPU support, and a smoother production experience.
AMD/Vulkan support remains experimental. CUDA is still the recommended backend for NVIDIA GPUs.
Since 1.0.94, Foundry grew into a broader local audio production platform with major advances in speech, GPU support, setup, automation, and usability.
.zvoice format and refreshed the bundled demonstration voice library.All AI generation, voice cloning, and audio processing happens locally on your GPU, nothing is uploaded to a server. However, an internet connection is required for login and license verification. The app may sign you out if it cannot reach the authentication server for an extended period. Your generated audio files and voice data never leave your machine.
Demodokos Foundry requires an NVIDIA GPU with at least 4 GB of VRAM. Any RTX series card will work well. 12 GB VRAM is recommended for best performance. GTX 1080 and newer cards are supported. AMD is experimentally supported for all Speech features, no Music.
Good news! Version 2.0 includes support for AMD, though without Music generation at this point. Speech and agentic features are experimentally available.
The Creator plan is $15.00/month with unlimited AI music and voice generation. The Professional plan is $49.00/month. A free 7-day trial is included, with no charge during the trial.
Yes. Demodokos Foundry offers a 7-day free trial with full access to all features. It is processed through PayPal with a $0 authorization, and you are not charged unless you choose to keep the subscription after the trial ends. Cancel anytime before the trial expires.
Yes. Demodokos Foundry includes a built-in voice cloning feature. Upload a short audio sample and Foundry clones the voice locally on your machine. The cloned voice can be used with any of the 40 emotion styles and 5 intensity levels, with unlimited generation at no extra cost.
No. All processing happens on your GPU. Your audio files, voice samples, and generated content never leave your computer. There are no cloud uploads and no data sent to external servers during generation.
Yes. Because all AI processing runs on your own hardware, your business content, client audio, proprietary voice recordings, internal scripts, and confidential narration never leaves your premises. No cloud vendor receives or retains your data. This gives your organization full data sovereignty and makes Demodokos Foundry naturally aligned with GDPR requirements without needing vendor data processing agreements for the generation itself. It is especially well-suited for companies, legal firms, healthcare, media agencies, and anyone working with sensitive or client-owned audio content.
Yes. Demodokos Foundry is fully AI-Act compliant.
ElevenLabs is a cloud-based voice service that charges per character generated and requires an internet connection. Demodokos Foundry runs entirely on your own PC, has no per-generation credits or limits, and processes everything offline. It also includes full music generation, a multi-track timeline editor, and stem separation. These are features ElevenLabs does not offer.
Yes. Subscriptions can be cancelled at any time, log into your account -> Billing -> Cancel. Cancellation takes effect at the end of the current billing period. No cancellation fees apply.
Demodokos Foundry supports music generation in 50 languages and speech and voice generation in 10 languages. The Creative AI music writing assistant currently operates in English.