MiniMax Speech 2.8发布，强化自然语音与声音克隆

MiniMax Speech 2.8: Breathing life into AI voice - MiniMax News | MiniMax (https://www.minimax.io/) ModelsLLM MiniMax M3 (https://www.minimax.io/models/text/m3) MiniMax M2.7 (https://www.minimax.io/models/text/m27) MiniMax M2.5 (https://www.minimax.io/models/text) VIDEO MiniMax H3 (https://www.minimax.io/blog/minimax-h3) SPEECH & MUSIC MiniMax Speech 2.8 (https://www.minimax.io/news/minimax-speech-28) MiniMax Music 3.0 (https://platform.minimax.io/docs/guides/music-generation) Product MiniMax Code (https://code.minimax.io) MiniMax Design (https://design.minimax.io/) Audio (https://www.minimax.io/audio) Talkie (https://www.talkie-ai.com/) APIToken PlanResearchMiniMax H3CompanyIntelligence with everyone About (https://www.minimax.io/about) News (https://www.minimax.io/news) Investor Relations (https://ir.minimax.io/) Contact Us (https://platform.minimax.io/contact-us) (https://www.minimax.io) ModelsLLM MiniMax M3NEW (https://www.minimax.io/models/text/m3) MiniMax M2.7 (https://www.minimax.io/models/text/m27) MiniMax M2.5 (https://www.minimax.io/models/text) VIDEO MiniMax H3NEW (https://www.minimax.io/blog/minimax-h3) SPEECH & MUSIC MiniMax Speech 2.8NEW (https://www.minimax.io/news/minimax-speech-28) MiniMax Music 3.0NEW (https://platform.minimax.io/docs/guides/music-generation) Product MiniMax CodeNEW (https://code.minimax.io) MiniMax Design (https://design.minimax.io/) Audio (https://www.minimax.io/audio) Talkie (https://www.talkie-ai.com/) APIToken PlanResearchMiniMax H3CompanyIntelligence with everyone About (https://www.minimax.io/about) News (https://www.minimax.io/news) Investor Relations (https://ir.minimax.io/) 2026.1.23MiniMax Speech 2.8: Breathing life into AI voice Access API (https://platform.minimax.io/docs/api-reference/speech-t2a-intro) Try Audio Now (https://www.minimax.io/audio) MiniMax Speech 2.8: Breathing Life into AI Voice Today, we are excited to introduce MiniMax Speech 2.8. This isn't just a technical upgrade; it's a breakthrough in vocal authenticity. By introducing native sound tag support, high-fidelity cloning, and studio-grade clarity, we are closing the gap between AI and the human voice. Our mission remains clear: to make synthetic speech feel truly human and indistinguishable. 1. Reclaiming the "Nuance": Teaching AI to Hesitate and Breathe In the past, AI voices often felt cold because they were "too perfect". Real human speech is filled with imperfect breaths, pauses, and hesitations—subtle signals that convey emotion and emphasize key points. Speech 2.8 introduces Native Sound Tags. By modeling colloquial fillers like "um," "uh," and "ah," we preserve the natural rhythm, pitch, and pauses of human dialogue. No more robotic, flattened speech; the warmth is in the details. Speech-2.8 Sound Tags Demo00:00 / 00:00 Text: "Hey, it's me. How are ya? (chuckle) I hope you're having an awesome day! We actually had a bit of a crazy launch day yesterday, you know, but (breath) I'm just recovered and ready to roll. You're listening to this and probably thinking I'm just chatting into a microphone, right? But here's the twist: (clear-throat) I'm actually not human. I am the new Speech 2.8 model from MiniMax. Crazy, right? (laughs) If you listen closely, you can hear how I handle the pacing, the little breaths, and even that casual vibe. Have a great day!" 2. Voice Cloning: Replicate Your "Vocal Fingerprint" in 10 Seconds We have optimized our feature extraction process to achieve a new level of similarity in voice cloning. With just a 10-second sample, Speech 2.8 precisely captures your unique texture, breathiness, and even your specific speaking pace. The result isn't just a voice that sounds "like" you—it is you. Original Audio00:00 / 00:00Speech-2.8 Cloned Result00:00 / 00:00This English demo showcases how Speech 2.8 captures the "soul" of a professional narrator: Authentic Conversationality: The voice has a "lived-in" quality. It doesn't sound like a stiff announcer; instead, it sounds like a trusted

MiniMax MiniMax Speech 2.8 MiniMax Speech 2.8 https://www.minimax.io/news/minimax-speech-28