On January 20, 2025, MiniMax, a subsidiary of Shanghai Xiyu Technology Co., Ltd., announced the global launch of its newly upgraded T2A-01 series voice models, along with the release of the Hailuo voice product. The T2A-01 series includes two models for users: T2A-01-HD and T2A-01-Turbo. The API service has also been launched on the MiniMax open platform, allowing enterprises to choose based on their audio quality and generation speed needs.
As a leading general artificial intelligence technology company, MiniMax focuses on developing various modalities of general large models, including a trillion-parameter MoE text model, a voice model, and an image model. Based on these models, MiniMax has launched native applications such as Xingye and Hailuo AI, and provides open platform API services for enterprises and developers. The newly released T2A-01 series voice models not only feature clear sound quality, natural rhythm, and precise emotional expression, but also support 17 languages including Chinese, Cantonese, English, Japanese, Korean, Arabic, and Spanish, along with hundreds of preset voice tones, providing a natural and smooth voice generation experience for both enterprise and individual users.
One of the highlights of Hailuo voice is its powerful multilingual synthesis capability. Supported by the T2A-01 model, Hailuo voice leads similar products in similarity, error rate, and auditory evaluation. In multiple languages including Chinese, Cantonese, English, Japanese, Korean, and Arabic, Hailuo voice significantly outperforms in similarity and accuracy, matching the comprehensive capabilities of the internationally leading model, ElevenLabs. Additionally, Hailuo voice has emotional understanding capabilities, allowing it to intelligently recognize and reproduce subtle emotional nuances in speech. Users can specify emotions as needed to generate voice outputs that accurately capture deep human emotions.
Hailuo voice also offers users a rich selection of voice tones and personalized adjustment features. Users can filter by language, accent, gender, and age to choose from over 300 preset voice tones and fine-tune them using effects such as adjusting tone clarity, intensity, and adding special effects like echo, broadcast, distortion, and electronic music to meet different scene requirements.
Hailuo Voice:
https://hailuoai.com/audio
Hailuo Audio (Overseas Version):
https://hailuo.ai/audio
Domestic API Service:
https://platform.minimaxi.com/document/T2A%20V2
Overseas API Service:
https://intl.minimaxi.com/document/T2A%20V2?key=66719005a427f0c8a5701643
