Connect with us

Hi, what are you looking for?

Top Stories

Kyrgyz NineNineSix Launches Kani TTS 2, Now Among Top 3 TTS Models on Hugging Face

Kyrgyz startup NineNineSix launches Kani TTS 2, a groundbreaking open-source text-to-speech model now ranking among the top three on Hugging Face, expanding linguistic inclusivity.

Kyrgyz startup NineNineSix launches Kani TTS 2, a groundbreaking open-source text-to-speech model now ranking among the top three on Hugging Face, expanding linguistic inclusivity.

Bishkek, Feb. 19, 2026. /Kabar/. Kyrgyz developers are making strides on the international technology stage, according to a report from the High-Tech Park (HTP) of Kyrgyzstan. The startup team NineNineSix has unveiled a new version of their speech synthesis model, Kani TTS 2, which has quickly gained popularity, now ranking among the top three text-to-speech (TTS) models on the Hugging Face platform, a leading repository for artificial intelligence models.

Kani TTS 2 marks a significant advancement from its predecessor, boasting the ability to generate up to 40 seconds of continuous speech in a single run, more than double the capacity of the original version. The HTP highlighted that achieving this ranking as a fully open-source model from Kyrgyzstan is a noteworthy accomplishment in the AI landscape.

Founded in Kyrgyzstan, NineNineSix is recognized for its innovative projects in language technology. The team previously developed the first version of Kani TTS and introduced AkylAi, the first AI capable of speaking Kyrgyz. Their focus on underrepresented languages sets them apart from larger AI firms that predominantly prioritize widely spoken languages such as English and Spanish.

Kani TTS 2 demonstrates versatility, supporting not only English and Spanish but also Kyrgyz. Its architecture allows for training in additional languages, accents, and dialects, making it a valuable tool for linguistic diversity. A distinctive aspect of the project is the publication of the complete pre-training code, enabling researchers and developers worldwide to create custom voice models based on Kani TTS 2.

Nursultan Bakashov, co-founder of NineNineSix, expressed enthusiasm about the new model, stating, “Kani TTS 2 is the next step after our first version: we’ve made speech generation more stable and taught the model to produce longer fragments. We focus on compact and open models—they’re easier to launch and adapt to different languages and accents, including resource-poor ones. It’s important for us to demonstrate that world-class technology can be created in Kyrgyzstan, so we’ve open-sourced not only the model weights but also the entire pre-training code—so any team can train a TTS from scratch for their language.”

Key enhancements in Kani TTS 2 include stable speech generation capabilities extending up to 40 seconds per run, zero-shot voice cloning—which allows for cloning a voice based on a brief audio sample—and a completely open architecture and training code. Its significant standing on Hugging Face reflects its growing recognition in the tech community.

The model is built on approximately 400 million parameters and was pre-trained on around 10,000 hours of speech data, allowing it to operate on GPUs with as little as 3 GB of video memory. This accessibility makes Kani TTS 2 suitable for both local and server-based applications.

The HTP remarked on the implications of such advancements: “Kani TTS 2 is not just another AI model. It is proof that Kyrgyzstani specialists are capable of creating world-class technologies and competing in the global artificial intelligence market. NineNineSix demonstrates that Kyrgyzstan can be not only a consumer but also a creator of advanced AI solutions.”

The success of Kani TTS 2 highlights the increasing importance of inclusivity in artificial intelligence development. As technology continues to evolve, the ability to cater to diverse linguistic needs positions Kyrgyzstan and its developers as pivotal players in the global AI landscape. The implications of this achievement extend beyond the immediate technical specifications, marking a significant step towards empowering underrepresented languages and showcasing the potential for innovation in resource-rich environments.

See also
Staff
Written By

The AiPressa Staff team brings you comprehensive coverage of the artificial intelligence industry, including breaking news, research developments, business trends, and policy updates. Our mission is to keep you informed about the rapidly evolving world of AI technology.

You May Also Like

Top Stories

Nvidia enters South Korea's AI market by launching 7 million Korean-language personas and the multimodal Nemotron3 Nano, aiming to establish market dominance.

Top Stories

Multiverse Computing unveils the LittleLamb AI model family on Hugging Face, reducing model size by 50% while enhancing performance for edge and mobile applications.

Top Stories

DeepSeek's V4-Pro eclipses GPT-5 and Claude in key benchmarks, achieving a Codeforces rating of 3,206 while undercutting OpenAI's costs by 89% per million tokens.

Top Stories

Hugging Face launches ML Intern, an open-source AI agent that surpasses Claude Code in scientific reasoning with a 32% GPQA score, offering $1,000 in...

Top Stories

Anonymous developer RizenML claims to have trained a 235M parameter language model on a single Nvidia RTX 5080 in 14 days, challenging traditional AI...

Top Stories

Threat actors exploit the Marimo Python notebook vulnerability (CVE-2026-39987) to deploy NKAbuse malware via Hugging Face, launching 662 attacks in just three days.

Top Stories

Hugging Face's HoloTab Chrome extension enables AI models to mimic human behavior in web applications, enhancing automation without site-specific integrations.

Top Stories

MiniMax launches the free M2.7 AI model with 229 billion parameters, outperforming Gemini 3.1 Pro in key benchmarks and enhancing multi-agent capabilities.

© 2025 AIPressa · Part of Buzzora Media · All rights reserved. This website provides general news and educational content for informational purposes only. While we strive for accuracy, we do not guarantee the completeness or reliability of the information presented. The content should not be considered professional advice of any kind. Readers are encouraged to verify facts and consult appropriate experts when needed. We are not responsible for any loss or inconvenience resulting from the use of information on this site. Some images used on this website are generated with artificial intelligence and are illustrative in nature. They may not accurately represent the products, people, or events described in the articles.