Ant Group Launches Ming-3.0 Speech Models for Voice Applications and Audio Understanding
- Published
- Source
- TechNode.com
Ant Group unveiled its Ming-3.0 speech model family on October 20, introducing five models that cater to speech synthesis, audio understanding, conversation, and speech recognition. Developers can leverage these models individually or in combination to create innovative voice-based applications.
The significance of these models lies in their advanced capabilities, including voice cloning from reference recordings and voice design through natural-language descriptions. Users can customize the output by specifying emotional tone, emphasis, and pacing, enhancing the user experience in various applications.
Ant Group's Ming-3.0 models are already integrated into services such as the Afu health app, Alipay search, and internal office tools. As the technology evolves, it will be important to monitor further developments and potential new applications in the voice technology landscape. No further timeline was disclosed at the time of publication.
Original report
Ant Group open-sources Ming-3.0 speech models with voice design and audio understanding
TechNode.com · TechNode FeedThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
Related Suppliers
Volarious (Tethered Drone System)
Singapore-based tethered drone system manufacturer enabling 24/7 persistent aerial surveillance for public safety, border patrol, and defense with cable.
TG0 (Tangi0 Ltd)
UK startup commercialising flexible polymer-based 3D touch and pressure sensing surfaces for consumer electronics, automotive, and healthcare products.
ShengShu Technology 生数科技
Beijing-founded AI company building general world models; its Motubrain product is a world-action model for physical robot control and embodied intelligence.
Inventrom Private Limited
Bengaluru startup founded 2012 making the Bolt IoT open hardware and cloud platform for STEM education in robotics, IoT, and machine learning in 62 countries.
Vocal Apps
French software company developing voice-directed work and chatbot AI applications for logistics and warehouse operations.
Beijing SinoVoice Technology 北京信诺达科技有限公司
Beijing AI company founded 2000; its Lingyun platform delivers speech, NLP, and OCR technology to finance, telecom, and government clients.
Datatang 数据堂(北京)科技股份有限公司
Beijing AI training-data supplier founded 2010 and quoted on NEEQ; its Nexdata arm sells egocentric, teleoperation and hand-pose datasets for robot learning.
ENERZAi
Seoul, South Korea edge-AI software firm founded 2019; its Optimium engine runs models at 1.58-bit quantization on Arm, Intel, and AMD chips.
Om AI 联汇科技
Hangzhou on-device multimodal AI company; VLX-Seek, VLX-Flow and VLX-Go models and the OmAgent platform give robots and drones perception and navigation.
iFLYTEK Co., Ltd. 科大讯飞股份有限公司
iFLYTEK is a Chinese public AI company (SZSE: 002230) whose AIUI voice-interaction platform powers robots, TVs, and smart hardware.
Motorika USA Inc (part of Hobart Healthcare)
US subsidiary of Israel's Motorika Medical; markets ReoAmbulator and ReoGo robotic rehabilitation systems for gait and upper-limb neurological therapy.
UCSD Healthcare Robotics Lab
UCSD robotics research lab led by Prof. Laurel Riek; focuses on human-robot teaming, assistive care robots, and healthcare AI in clinical settings.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.