Xiaomi has launched the MiMo-V2.5-TTS series, a new line of text-to-speech models, available through the MiMo open platform API. The series, which is free during its public testing phase, includes three models designed for various applications. MiMo-V2.5-TTS offers high-quality voice tones and a singing mode that accurately captures pitch and rhythm. MiMo-V2.5-TTS-VoiceDesign allows users to create new voice tones from a single description, while MiMo-V2.5-TTS-VoiceClone enables voice cloning with minimal reference audio.
These models support natural language commands for speech style adjustments, such as "gentle but tired," and precise control via audio tags like "inhale" or "sob." They support multiple languages, including Chinese, English, and regional dialects, with audio output sampled at 24,000 Hz. This release marks a significant advancement in Xiaomi's text-to-speech capabilities, offering versatile and customizable voice solutions.
Xiaomi Unveils MiMo-V2.5-TTS Series with Advanced Voice Features
Disclaimer: The content provided on Phemex News is for informational purposes only. We do not guarantee the quality, accuracy, or completeness of the information sourced from third-party articles. The content on this page does not constitute financial or investment advice. We strongly encourage you to conduct you own research and consult with a qualified financial advisor before making any investment decisions.
