Today for AI
HOT RADAR
llmHEAT 0.0°

AI CURATED HOT STORY · 10/20/2026

Ant Group Open-Sources Ming-3.0-tts, Tops Voice Synthesis Leaderboard

4 reports archived0 independent sourcesupdated 10/23/2026, 05:23:43
Synthesis & Latest Updates

Ant Group's Ling AGI team has open-sourced the Ming-3.0 voice series, with its core component, Ming-3.0-tts, ranking first among open-source models on the Artificial Analysis leaderboard for controlled speech and pronunciation robustness. Available in 0.5B dense and 7.9B Mixture-of-Experts (MoE) versions under the MIT license, this release signifies a major leap in domestic open-source voice technology, surpassing several commercial competitors.

Data confirms that Ming-3.0-tts achieved a 93.2% score in pronunciation robustness tests and an Elo rating of 1069 in controlled speech arenas, outperforming models like Eleven v4. Technically, the series introduces a 'Director Mode' allowing precise control over emotion, stress, and rhythm via text descriptions, alongside stateless voice cloning. Complementary ASR and audio understanding models enhance long-audio processing by preserving non-textual context and improving dialect recognition accuracy.

This open-source initiative lowers development barriers by offering high-performance voice synthesis bases and modular workflows. It is poised to accelerate the deployment of voice interaction technologies in intelligent customer service, content creation, and accessibility services, reshaping the competitive landscape of the open-source voice ecosystem.

LATEST/Ming-3.0-tts weights are now available on Hugging Face. Developers can access both 0.5B and 7.9B MoE versions. The model is already integrated into Alipay's internal services, while the community explores fine-grained emotional dubbing using its 'Director Mode,' with complementary multimodal audio understanding models entering beta testing.

Hourly heat curve

168 fully observed hours
Now
0.0
Peak
26.208:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 4 reports · Latest first
  1. Artificial Analysis (@ArtificialAnlys)T1·78 pts

    Ant Group Open-Sources Ming-3.0-tts: Top-Tier TTS in 0.5B Params

    • Ming-3.0-tts is the only sub-1B parameter model in the top 3; all other top-10 open-weight TTS models are 3.5B or larger.
    • The model is released under the permissive MIT license, allowing commercial use and modification.
    • It achieves a 7x to 70x reduction in parameter count compared to peers at the same performance tier, significantly lowering compute requirements.
  4. IT之家 · 智能时代T2·78 pts

    Ant Group Open-Sources Ming-3.0 Voice Models with Director Mode and Long Audio Understanding

    • Ming-3.0-tts supports text-based voice design and 'Director Mode' to control performance details like emotion, stress, and rhythm.
    • Ming-3.0-audio-flash/tiny directly processes long audio for transcription, summarization, and opinion analysis, preserving non-textual context.
    • Ming-3.0-asr-tiny leverages LLM bases and hotword lists to improve recognition accuracy in dialects and vertical domains.