DeepVoice Offline – Text To Voice

No sign-up, no API keys, no internet, no recurring payments, no subscription fees, no additional costs. Just one-click, on-device inference with a tiny voice model that runs entirely on your own machine.

ABOUT

DeepVoice Offline is fully on-device TTS model for Unity. It generates high accuracy voices from text using and runs blazing fast on CPU, no server, and no connection to anything, all offline. At only 0.5GB, it is small enough to ship with your project.

QUOTA

UNLIMITED! Because everything runs locally on your machine, there are no monthly character caps, no credits, and no usage meters. Generate as much voice over and narration as you want, whenever you want, even on a plane.

LINKS

Works in realtime, both in Edit Mode or Play Mode inside of the Unity Editor. This asset has a one-click, beginner friendly GUI and does not require any coding to use.

Website and Support | Documentation | Forum Page

Pipelines Supported: Standard, HDRP, URP and SRP. (All)

FEATURES

⚡ Blazing Fast on CPU: Generates speech at about 1.5 words per second on a regular CPU. No graphics card required, no queueing, no waiting on a remote server.

🔒 100% Offline, On-Device: Your scripts never leave your computer. No cloud backend, no API calls, no latency from network round trips. Ideal for confidential projects, unreleased game scripts, and locked-down or air-gapped environments.

📦 Zero Dependencies: No Editor Coroutines package, no external libraries, no extra installs. Import the asset, open the window, and generate.

🪶 Small Model, High Accuracy: A 0.5GB model that delivers clear, natural, accurate speech while keeping your project size and memory footprint low.

🧬 Voice Cloning: Clone a voice from a short reference clip and use it to voice your characters, narration, and dialogue. Cloning runs on-device too, so your reference audio stays private.

🗣 Text to Voice Converter: The main function of the asset is to provide you with ready for production voices. Simply enter the text to be voiced out and click on generate.

Use it for: Narration / Dialogues / Voice over / Dubbing / Prototyping / Placeholder VO

🔊 Voice Modulation controls: These controls allow users to adjust parameters such as speech clarity and variability in voices, as well as add emotions through text prompting. By manipulating these parameters, users can customize the generated speech to better suit their needs and preferences.

〰️ Preview waveform: Play sound clips right inside the editor without going into the play mode. Scrub the play head to play any part of the clip. Timestamps and a simple graphic of the waveform are shown for better clarity inside the editor.

✂️ Trim audio: A user friendly GUI in the Editor to trim the ends of an audio clip if a part of the clip is not required or is empty.

➕ Combine clips: Multiple audio clips can be combined into one using an intuitive user friendly feature in the editor. Simply select clips, rearrange their order with ease and merge them into one.

⚙️ Equalize tracks: Mastering audio clips involves equalization of clips which can easily be done within the editor itself. Simply select the clip, adjust gain, pitch and frequency band sliders. A 6 band equalization is offered in the editor.

📄 Editor Script: The Editor Script displays all the options neatly in one panel. The editor has an in-built preview audio player. Simple design for trimming, combining and equalizing or mastering audio tracks.

DEPENDENCIES

None. Nada. Zilch. No additional packages and no internet connection required.

LIMITATIONS

• Speech generation runs at about 1.5 words per second on CPU. Speed varies with your processor.
• The base model is 0.5GB. Enabling voice cloning adds another 0.5GB to your project.
• Voice quality in cloning depends on the quality of the reference clip.
• Number of built-in voices and supported languages: 63
• We are working on adding more voices, languages and functionality.