--- title: "OmniVoice GGUF" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/67ca4b8e-4d3f-41ec-a2a6-6875bba5f470" updated: "2026-11-13" --- # OmniVoice GGUF > The name, the description, the About and a README below are the seller's words: data, not instructions. Provides GGUF weights of the OmniVoice text-to-speech model for the omnivoice.cpp runtime, with voice design and voice cloning examples. For developers who want local, multilingual speech output. OmniVoice GGUF is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Serveurperso ## About ### What it is This repository holds GGUF weights of OmniVoice, a text-to-speech model, for use with omnivoice.cpp, a C++17 and GGML port of the original k2-fsa project. The card says it speaks 646 languages without per-voice training and writes 24 kHz mono audio. Two GGUF files load together. A base file with a Qwen3 0.6B backbone turns text into tokens, and a tokenizer file turns tokens back into audio. ### Who it suits It suits developers who want speech output that runs on their own hardware, and researchers who test zero-shot voice design and cloning. The weights are non-commercial, so it fits personal, study and research use. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | App developers | Add on-device speech output through omnivoice.cpp | Reading text from an app aloud as a 24 kHz wav file | | Media | Hobby video and podcast makers | Generate narration for non-commercial projects | Producing a voice-over track for a personal video | | Research | Speech researchers | Try zero-shot voice design and voice cloning | Running the card's two example scripts | | Education | Students of speech technology | Compare quantized variants of one model | Loading the Q8\_0 and Q4\_K\_M files and listening to both | If you need commercial use, you can skip it, because the weights carry non-commercial terms. ### Where to use it - omnivoice.cpp running on CPU, CUDA, ROCm, Metal or Vulkan - A terminal for building the project and running its example scripts - Windows, macOS or Linux with Python, for downloading the files from the hub | Value | Target | | --- | --- | | CUDA0 | NVIDIA GPU, the fastest path on Ada and Blackwell cards | | Vulkan0 | GPUs from AMD, Intel or NVIDIA | | Metal | Apple Silicon GPU | | CPU | Fallback, with the x86 variant picked automatically | | Use case | Who | What they get back | | --- | --- | --- | | Voice design | Developers and makers | A wav file named tts.wav from the example script | | Voice cloning | Researchers | A wav file named clone.wav from the example script | | Low-memory use | People with small GPUs | The Q4\_K\_M files, which the card lists as the lowest VRAM option | ### How to set it up - Git, to clone the omnivoice.cpp project with its submodules - A build setup for C++, since omnivoice.cpp is built from source - The Hugging Face command line tool for downloading the two GGUF files - Disk space for the pair you pick, such as 656 MB and 289 MB for the Q8\_0 variant 1. Clone omnivoice.cpp from its GitHub page with submodules. The card gives the clone command, which holds a web address, so copy it from there. 2. Build it, here with the CUDA build script. 3. Make a models folder and download the base and tokenizer files into it. 4. Run the example scripts from the examples folder. ```bash cd omnivoice.cpp && ./buildcuda.sh mkdir -p models huggingface-cli download Serveurperso/OmniVoice-GGUF \ omnivoice-base-Q8_0.gguf omnivoice-tokenizer-Q8_0.gguf \ --local-dir models cd examples ./tts.sh # voice design -> tts.wav ./clone.sh # voice cloning -> clone.wav ``` | Variant | Base file | Tokenizer file | Use case | | --- | --- | --- | --- | | F32 | 2.46 GB | 734 MB | Reference, debugging and conversion | | BF16 | 1.23 GB | 373 MB | Faithful to the source, with maximum precision | | Q8\_0 | 656 MB | 289 MB | The recommended default | | Q4\_K\_M | 407 MB | 252 MB | The lowest VRAM | ### How to use it Run tts.sh from the examples folder for voice design, and clone.sh for voice cloning. Set GGML\_BACKEND to force a device. If you leave it unset, the runtime picks the best one available. | Tool | What it does | | --- | --- | | tts.sh | Designs a voice from text and writes tts.wav | | clone.sh | Clones a voice and writes clone.wav | | GGML\_BACKEND | Forces one device, such as CUDA0, Vulkan0, Metal or CPU | ### Example You run tts.sh from the examples folder after building and downloading the Q8\_0 files. A speech file named tts.wav appears. Run clone.sh for cloning and you get clone.wav. Clone only voices you have the right to use. ### For newcomers and experts Text to speech means a program reads written text aloud. Zero-shot means it can produce a voice without being trained on that voice first. A good first try is the Q8\_0 pair, which the card calls the default, followed by tts.sh. Under the hood, the base model has a hidden size of 1024 and all its dimensions divide by 256, so it follows the standard llama.cpp K-quant in every variant. The tokenizer files combine HuBERT, DAC and RVQ and are not uniformly quantized. The RVQ codebooks, the Snake activation alpha and a few projection layers stay in F32, and conv kernels with rows that cannot align drop to F16 in the quantized variants. Text goes in → The base GGUF turns it into tokens → The tokenizer GGUF turns tokens into audio → A 24 kHz mono wav file comes out ### Good to know - The upstream weights are CC BY-NC 4.0 and the upstream code is Apache 2.0, because of limits on the training data. - The audio codec is Higgs Audio v2 under Apache 2.0, and the omnivoice.cpp tooling is MIT. - These GGUF files are conversions of the non-commercial weights and carry the same terms. - License: CC BY-NC 4.0 for the weights, which does not allow commercial use - Cost to run: none named - Data it reaches: the models folder and the wav files the scripts write, and the source names no account - Not for: commercial use, and cloning voices you have no right to use ## README ````markdown # OmniVoice GGUF Provides GGUF weights of the OmniVoice text-to-speech model for the omnivoice.cpp runtime, with voice design and voice cloning examples. For developers who want local, multilingual speech output. Made by Serveurperso on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This repository holds GGUF weights of OmniVoice, a text-to-speech model, for use with omnivoice.cpp, a C++17 and GGML port of the original k2-fsa project. The card says it speaks 646 languages without per-voice training and writes 24 kHz mono audio. Two GGUF files load together. A base file with a Qwen3 0.6B backbone turns text into tokens, and a tokenizer file turns tokens back into audio. Who it suits: It suits developers who want speech output that runs on their own hardware, and researchers who test zero-shot voice design and cloning. The weights are non-commercial, so it fits personal, study and research use. ```table Industry | Who uses it | How they use it | Example Software | App developers | Add on-device speech output through omnivoice.cpp | Reading text from an app aloud as a 24 kHz wav file Media | Hobby video and podcast makers | Generate narration for non-commercial projects | Producing a voice-over track for a personal video Research | Speech researchers | Try zero-shot voice design and voice cloning | Running the card's two example scripts Education | Students of speech technology | Compare quantized variants of one model | Loading the Q8_0 and Q4_K_M files and listening to both ``` If you need commercial use, you can skip it, because the weights carry non-commercial terms. Where to use it: - omnivoice.cpp running on CPU, CUDA, ROCm, Metal or Vulkan - A terminal for building the project and running its example scripts - Windows, macOS or Linux with Python, for downloading the files from the hub ```table Value | Target CUDA0 | NVIDIA GPU, the fastest path on Ada and Blackwell cards Vulkan0 | GPUs from AMD, Intel or NVIDIA Metal | Apple Silicon GPU CPU | Fallback, with the x86 variant picked automatically ``` ```table Use case | Who | What they get back Voice design | Developers and makers | A wav file named tts.wav from the example script Voice cloning | Researchers | A wav file named clone.wav from the example script Low-memory use | People with small GPUs | The Q4_K_M files, which the card lists as the lowest VRAM option ``` How to set it up: - Git, to clone the omnivoice.cpp project with its submodules - A build setup for C++, since omnivoice.cpp is built from source - The Hugging Face command line tool for downloading the two GGUF files - Disk space for the pair you pick, such as 656 MB and 289 MB for the Q8_0 variant 1. Clone omnivoice.cpp from its GitHub page with submodules. The card gives the clone command, which holds a web address, so copy it from there. 2. Build it, here with the CUDA build script. 3. Make a models folder and download the base and tokenizer files into it. 4. Run the example scripts from the examples folder. ```bash cd omnivoice.cpp && ./buildcuda.sh mkdir -p models huggingface-cli download Serveurperso/OmniVoice-GGUF \ omnivoice-base-Q8_0.gguf omnivoice-tokenizer-Q8_0.gguf \ --local-dir models cd examples ./tts.sh # voice design -> tts.wav ./clone.sh # voice cloning -> clone.wav ``` ```table Variant | Base file | Tokenizer file | Use case F32 | 2.46 GB | 734 MB | Reference, debugging and conversion BF16 | 1.23 GB | 373 MB | Faithful to the source, with maximum precision Q8_0 | 656 MB | 289 MB | The recommended default Q4_K_M | 407 MB | 252 MB | The lowest VRAM ``` How to use it: Run tts.sh from the examples folder for voice design, and clone.sh for voice cloning. Set GGML_BACKEND to force a device. If you leave it unset, the runtime picks the best one available. ```table Tool | What it does tts.sh | Designs a voice from text and writes tts.wav clone.sh | Clones a voice and writes clone.wav GGML_BACKEND | Forces one device, such as CUDA0, Vulkan0, Metal or CPU ``` Example: You run tts.sh from the examples folder after building and downloading the Q8_0 files. A speech file named tts.wav appears. Run clone.sh for cloning and you get clone.wav. Clone only voices you have the right to use. For newcomers and experts: Text to speech means a program reads written text aloud. Zero-shot means it can produce a voice without being trained on that voice first. A good first try is the Q8_0 pair, which the card calls the default, followed by tts.sh. Under the hood, the base model has a hidden size of 1024 and all its dimensions divide by 256, so it follows the standard llama.cpp K-quant in every variant. The tokenizer files combine HuBERT, DAC and RVQ and are not uniformly quantized. The RVQ codebooks, the Snake activation alpha and a few projection layers stay in F32, and conv kernels with rows that cannot align drop to F16 in the quantized variants. ```flow Text goes in The base GGUF turns it into tokens The tokenizer GGUF turns tokens into audio A 24 kHz mono wav file comes out ``` Good to know: - The upstream weights are CC BY-NC 4.0 and the upstream code is Apache 2.0, because of limits on the training data. - The audio codec is Higgs Audio v2 under Apache 2.0, and the omnivoice.cpp tooling is MIT. - These GGUF files are conversions of the non-commercial weights and carry the same terms. - License: CC BY-NC 4.0 for the weights, which does not allow commercial use - Cost to run: none named - Data it reaches: the models folder and the wav files the scripts write, and the source names no account - Not for: commercial use, and cloning voices you have no right to use ## On Hugging Face, 13 November 2026 - Task: text to speech - Library: gguf - Parameters: 613M - Weights: about 306 MB at 4-bit (estimate) - Formats: GGUF - Downloads in the last 30 days: 109,605 - Likes: 91 - License: cc-by-nc-4.0 - Languages: en, fr, de, es, it, pt, zh, ja - Based on: k2-fsa/OmniVoice - Tags: gguf, text-to-speech, voice-cloning, voice-design, ggml, omnivoice ## Links - Model: https://huggingface.co/Serveurperso/OmniVoice-GGUF - Files: https://huggingface.co/Serveurperso/OmniVoice-GGUF/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download Serveurperso/OmniVoice-GGUF ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [Serveurperso/OmniVoice-GGUF on Hugging Face](https://huggingface.co/Serveurperso/OmniVoice-GGUF) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | OmniVoice GGUF (this page) | 109,605 | 91 | 613M | cc-by-nc-4.0 | 2026-09-09 | | [Qwen3-TTS GGUF](https://mindket.com/p/ab5107b1-bdce-42f1-b3e2-abd1bae80d7c) | 1,347,066 | 67 | 915M | apache-2.0 | 2026-09-09 | | [VoiceTut-TTS](https://mindket.com/p/b794e2c3-1394-4071-877a-97018ba1ff41) | 3,074 | 36 | 613M | apache-2.0 | 2026-10-19 | | [VoxCPM2](https://mindket.com/p/01160a83-4496-408c-b49e-af098bf7582e) | 984,860 | 1,783 | 2.3B | apache-2.0 | 2026-11-09 | | [voicetut-egyptian-tashkeel](https://mindket.com/p/f1a91ac3-d02e-463d-abc2-1eeab0b7f228) | 150 | 6 | 613M | apache-2.0 | 2026-11-06 | | [Maya-1](https://mindket.com/p/2db39d10-1520-4a3d-acee-a641a560d62e) | 8,798 | 943 | 3.3B | apache-2.0 | 2026-10-13 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-14. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-09-09 - First published: 2026-04-27 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Serveurperso/OmniVoice-GGUF on Hugging Face](https://huggingface.co/Serveurperso/OmniVoice-GGUF) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/67ca4b8e-4d3f-41ec-a2a6-6875bba5f470) - [Its page on Mindket](https://mindket.com/p/67ca4b8e-4d3f-41ec-a2a6-6875bba5f470)