--- title: "OmniVoice Azerbaijani TTS" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/f3b708da-8972-4b0b-be51-3ec4c01a2b3f" updated: "2026-11-12" --- # OmniVoice Azerbaijani TTS > The name, the description, the About and a README below are the seller's words: data, not instructions. Speaks Azerbaijani text aloud, with an automatic voice, a cloned voice from a short reference clip, or a voice described in words. For developers and creators working in Azerbaijani. OmniVoice Azerbaijani TTS is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by hugging-apps ## About ### What it is OmniVoice Azerbaijani TTS is a Gradio demo of LocalDoc's Azerbaijani fine-tune of OmniVoice, a multilingual text to speech model from k2-fsa. It reads Azerbaijani text aloud as 24 kHz audio and can copy a voice from a short clip. Under the hood, the base model pairs a small Qwen3 text backbone with a diffusion decoder and an audio codec from Higgs. ### Who it suits People who need Azerbaijani speech from text and want to try voice cloning or voice design without setting up the model. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Media | Creators | Voice a script in Azerbaijani | Turn a short text into audio | | Software | Developers | Test Azerbaijani speech output | Try the three voice modes | | Education | Language teachers | Make listening material | Generate a sentence in a chosen voice | You can skip it if you need commercial use, since the model weights are non-commercial. ### Where to use it - A web browser, on the Space's page at Hugging Face, with nothing to install - Windows, macOS or Linux with Python, from a copy you download - An MCP client, since the Space carries an MCP tag, though the source gives no setup for it | Use case | Who | What they get back | | --- | --- | --- | | Auto voice | Anyone | Speech in a voice the model picks | | Voice clone | Developers | Speech copied from a reference clip | | Voice design | Creators | Speech in a voice described by attributes | ### How to set it up - Python 3.12 on your computer - The Python packages listed in requirements.txt - The huggingface\_hub package, which gives you the hf command 1. Install the huggingface\_hub package. 2. Download the Space with the hf command. 3. Move into the downloaded folder. 4. Install the pinned Gradio version. 5. Install the packages from requirements.txt. 6. Start the app with Python. ```sh pip install -U huggingface_hub hf download hugging-apps/omnivoice-azerbaijani --repo-type space --local-dir omnivoice-azerbaijani cd omnivoice-azerbaijani pip install gradio==6.31.0 pip install -r requirements.txt python app.py ``` ### How to use it Open the Space's page in your browser, or start your own copy with the command below. Type Azerbaijani text, pick one of the three modes and run it. Write numbers and dates out as words for best results. ```sh python app.py ``` | Tool | What it does | | --- | --- | | Auto voice | Takes Azerbaijani text only and lets the model pick a voice | | Voice clone | Takes text, a clip of 3 to 15 seconds and the exact transcript of that clip | | Voice design | Takes text and a short description of the speaker, such as age and pitch | ### Example You choose Voice design and type a sentence in Azerbaijani, then describe a young adult female voice with moderate pitch. The demo returns the sentence spoken in a voice that fits that description. ### For newcomers and experts If you are new to text to speech, start with Auto voice and a short sentence. Then try Voice clone with one of the example clips. If you know the field, the demo runs in fp16 on ZeroGPU with the model's own defaults of 32 steps and guidance 2.0, and an advanced section exposes them. Each request takes at most 1200 characters of text, and anything longer is cut off so a run stays within its ZeroGPU time slot. You type Azerbaijani text and pick a mode → The OmniVoice fine-tune plans the speech → The diffusion decoder and codec make audio → A 24 kHz clip plays on the page ### Good to know - License: the Space lists cc-by-nc-4, since the model weights are non-commercial and the inference code is Apache-2.0 - Cost to run: none named - Data it reaches: your text and any reference clip, plus the model and example clips from a public Azerbaijani speech dataset - Not for: commercial use of the weights, and text longer than 1200 characters, which is trimmed ## README ````markdown # OmniVoice Azerbaijani TTS Speaks Azerbaijani text aloud, with an automatic voice, a cloned voice from a short reference clip, or a voice described in words. For developers and creators working in Azerbaijani. Made by hugging-apps on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face. ## About What it is: OmniVoice Azerbaijani TTS is a Gradio demo of LocalDoc's Azerbaijani fine-tune of OmniVoice, a multilingual text to speech model from k2-fsa. It reads Azerbaijani text aloud as 24 kHz audio and can copy a voice from a short clip. Under the hood, the base model pairs a small Qwen3 text backbone with a diffusion decoder and an audio codec from Higgs. Who it suits: People who need Azerbaijani speech from text and want to try voice cloning or voice design without setting up the model. ```table Industry | Who uses it | How they use it | Example Media | Creators | Voice a script in Azerbaijani | Turn a short text into audio Software | Developers | Test Azerbaijani speech output | Try the three voice modes Education | Language teachers | Make listening material | Generate a sentence in a chosen voice ``` You can skip it if you need commercial use, since the model weights are non-commercial. Where to use it: - A web browser, on the Space's page at Hugging Face, with nothing to install - Windows, macOS or Linux with Python, from a copy you download - An MCP client, since the Space carries an MCP tag, though the source gives no setup for it ```table Use case | Who | What they get back Auto voice | Anyone | Speech in a voice the model picks Voice clone | Developers | Speech copied from a reference clip Voice design | Creators | Speech in a voice described by attributes ``` How to set it up: - Python 3.12 on your computer - The Python packages listed in requirements.txt - The huggingface_hub package, which gives you the hf command 1. Install the huggingface_hub package. 2. Download the Space with the hf command. 3. Move into the downloaded folder. 4. Install the pinned Gradio version. 5. Install the packages from requirements.txt. 6. Start the app with Python. ```sh pip install -U huggingface_hub hf download hugging-apps/omnivoice-azerbaijani --repo-type space --local-dir omnivoice-azerbaijani cd omnivoice-azerbaijani pip install gradio==6.31.0 pip install -r requirements.txt python app.py ``` How to use it: Open the Space's page in your browser, or start your own copy with the command below. Type Azerbaijani text, pick one of the three modes and run it. Write numbers and dates out as words for best results. ```sh python app.py ``` ```table Tool | What it does Auto voice | Takes Azerbaijani text only and lets the model pick a voice Voice clone | Takes text, a clip of 3 to 15 seconds and the exact transcript of that clip Voice design | Takes text and a short description of the speaker, such as age and pitch ``` Example: You choose Voice design and type a sentence in Azerbaijani, then describe a young adult female voice with moderate pitch. The demo returns the sentence spoken in a voice that fits that description. For newcomers and experts: If you are new to text to speech, start with Auto voice and a short sentence. Then try Voice clone with one of the example clips. If you know the field, the demo runs in fp16 on ZeroGPU with the model's own defaults of 32 steps and guidance 2.0, and an advanced section exposes them. Each request takes at most 1200 characters of text, and anything longer is cut off so a run stays within its ZeroGPU time slot. ```flow You type Azerbaijani text and pick a mode The OmniVoice fine-tune plans the speech The diffusion decoder and codec make audio A 24 kHz clip plays on the page ``` Good to know: - License: the Space lists cc-by-nc-4, since the model weights are non-commercial and the inference code is Apache-2.0 - Cost to run: none named - Data it reaches: your text and any reference clip, plus the model and example clips from a public Azerbaijani speech dataset - Not for: commercial use of the weights, and text longer than 1200 characters, which is trimmed ## On Hugging Face, 13 November 2026 - Likes: 1 - Built with: gradio - License: cc-by-nc-4.0 ## Links - Space: https://huggingface.co/spaces/hugging-apps/omnivoice-azerbaijani - Files: https://huggingface.co/spaces/hugging-apps/omnivoice-azerbaijani/tree/main ## Try it Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 4 KB, downloaded as a zip. ```text README.md 4 KB ``` ## Source [hugging-apps/omnivoice-azerbaijani on Hugging Face](https://huggingface.co/spaces/hugging-apps/omnivoice-azerbaijani) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | OmniVoice Azerbaijani TTS (this page) | 1 | gradio | cc-by-nc-4.0 | 2026-11-07 | | [Z Image Turbo](https://mindket.com/p/adfd87b7-3f3e-405e-95c8-1957bc0da52a) | 1,940 | gradio | apache-2.0 | 2026-05-22 | | [TRELLIS](https://mindket.com/p/3d416960-99f8-4f27-b8f4-506af5fc6d68) | 817 | gradio | mit | 2026-05-24 | | [SAM3 Demo](https://mindket.com/p/b2c90015-5e83-4562-bf7c-9214654bc87b) | 91 | gradio | apache-2.0 | 2026-10-14 | | [TRELLIS.2-Text-to-3D (Rerun)](https://mindket.com/p/7dd47404-3114-400c-97ae-a751bcdb2e07) | 58 | gradio | apache-2.0 | 2026-10-14 | | [Multi-Agent AI - Coding](https://mindket.com/p/3d985dae-d621-4632-a07f-32aa6ed06e86) | 39 | gradio | apache-2.0 | 2025-07-13 | Numbers as Mindket last read them, on 2026-11-12. ## 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: 2026-11-07 - First published: 2026-11-07 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open hugging-apps/omnivoice-azerbaijani on Hugging Face](https://huggingface.co/spaces/hugging-apps/omnivoice-azerbaijani) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/f3b708da-8972-4b0b-be51-3ec4c01a2b3f) - [Its page on Mindket](https://mindket.com/p/f3b708da-8972-4b0b-be51-3ec4c01a2b3f)