Skip to content
Hot eventDeveloping

inclusionAI Releases Ming-3.0-tts-tiny MoE Speech Synthesis Model

1 reports1 reporting sourcesUpdated 18 h ago

Start here

AI digest

inclusionAI released Ming-3.0-tts-tiny, a mixture-of-experts text-to-speech checkpoint built on the Ling V3 backbone with 7.9B total parameters and about 1.3B active per token, under the MIT license. The model supports zero-shot voice cloning, voice design from text descriptions, free-form style control, 14 inline paralinguistic tags, emotion, speed, pitch and volume control, multi-speaker podcast scripts, and Chinese, English, German, Spanish, French, Korean, Japanese, Sichuanese and Cantonese. The Hugging Face repository only distributes weights and does not provide a standalone inference setup; running the model requires the Ming-3.0-tts GitHub repository. Tiny uses a separate reference environment of Python 3.10.15, PyTorch and torchaudio 2.7.1+cu118, and transformers==4.46.3. Serving is documented for vLLM-Omni and SGLang-Omni through an OpenAI-compatible /v1/audio/speech endpoint.

Generated from reports · updated 9 h ago

Report timeline

Follow the reports to see the event from different sides.

November 19
  1. inclusionAI ModelsPicks
    inclusionAI releases Ming-3.0-tts-tiny, a 7.9B-A1.3B MoE speech synthesis model

    inclusionAI released Ming-3.0-tts-tiny, a mixture-of-experts TTS checkpoint built on the Ling V3 backbone with 7.9B total parameters and about 1.3B active per token, under the MIT license. It supports zero-shot voice cloning, voice design from text descriptions, free-form style control, 14 inline paralinguistic tags, emotion, speed, pitch and volume control, multi-speaker podcast scripts, and Chinese, English, German, Spanish, French, Korean, Japanese plus Sichuanese and Cantonese dialects. The Hugging Face repo only distributes weights; inference needs the Ming-3.0-tts GitHub repo, and serving is documented for vLLM-Omni and SGLang-Omni via an OpenAI-compatible /v1/audio/speech endpoint.

Heat for this event

Current, comparable range
6
Peak, comparable range
8November 19 18:00
Change in 24 hours
–

The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.