Ming-3.0-tts
A family of open speech models from Ant Group: a dense 0.5B based on Qwen2.5-0.5B and the MoE version tiny (7.9B parameters, about 1.3B active, based on Ling V3). They clone a voice from a short sample, create a voice from a description in words, and control delivery, emotion, speed, pitch and volume. There are more than 100 built-in Chinese voices, five English ones and 14 inline tags for a breath, cough, laugh, sigh and hesitation. Languages: Chinese, English, German, Spanish, French, Korean, Japanese and the Sichuanese and Cantonese dialects, no Russian. Sample rate is 44.1 kHz. Running it needs the code from the GitHub repository, and the Hugging Face page only distributes the weights. There is a Comfy-Org build for ComfyUI.
A voice may only be cloned with the consent of its owner. Recording someone else's voice without permission and passing it off as genuine is a separate legal and reputational risk; agree the process with a lawyer.
- Developer
- inclusionAI (Ant Group), China
- First release
- Sep 2026
- Latest release
- Oct 2026
- Sizes
- 0.5B and 7.9B-A1.3B (tiny)
- License
- Commercial use allowedMIT
- Russian
- Not supported
- Running
- On your own serverNeeds a GPU
- Industries
- Media and production, Customer support
What it does
- voicing videos and podcasts in Chinese and English with emotion control
- cloning a voice from a short sample
- creating a voice from a description for games and apps
Where it is used
Hardware requirements
Versions
- Ming-3.0-TTS для ComfyUI
- Ming-3.0-tts-tiny (7.9B-A1.3B)
- Ming-3.0-tts-0.5B
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can Ming-3.0-tts be used in a commercial project?
Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does Ming-3.0-tts need?
At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does Ming-3.0-tts support Russian?
No. The developer documentation lists the supported languages and Russian is not among them.
Where can I download Ming-3.0-tts and what does it cost?
The Ming-3.0-tts weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
Speech synthesis with voice cloning and emotion control in 80+ languages, including Russian. Quality is close to paid services, but the weights are for research only. The new Drama 3 (35B, 3B active) voices scenes with several characters (up to 16 voices in one text), understands tags such as a sigh or a laugh, over 80 languages, Russian is in the list.
DetailsText to speechCosyVoice / Fun-CosyVoiceAlibaba (Tongyi, FunAudioLLM) · ChinaCommercial use allowedSpeech synthesis with voice cloning from a short sample and streaming output for live dialogue. Version 3 supports 9 languages, including Russian.
DetailsSpeech to textVibeVoiceMicrosoft · USACommercial use allowedMicrosoft speech models: long multi-voice dialogue synthesis, fast synthesis for live conversation, and recognition of long recordings split by speaker, including in Russian.
DetailsSource: huggingface.co/inclusionAI/Ming-3.0-tts-0.5B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.