MiniMax Speech 2.8
MiniMax's studio-grade speech model with 332 voices, emotion control, voice cloning, and a 50,000-character input limit.
From MiniMax, Speech 2.8 is a cloud text-to-speech model. It converts written text into natural, spoken audio. It offers a choice of 39 voices and supports multiple languages. Voices can be tuned for speed and emotion, and output is available as MP3, WAV, FLAC, OGG, and PCM. It runs through Runware, Replicate, and MiniMax using your own API key, from $0.10 per 1,000 characters.
- Released
- 8 months ago (Jan 2026)
- Pricing
- $0.10 / 1k chars
- Type
- Text-to-speech
- Voices
- 39 to choose from
- Languages
- Multilingual
- Voice controls
- Speed, Emotion
- Output formats
- MP3, WAV, FLAC, OGG, PCM
Examples
Generated with Speech 2.8 via Runware: the same three scripts read by every text-to-speech model in the catalog, so the only thing that changes between two models’ clips is the model. Each model uses its own default voice; there is no shared voice to hold constant.
Baseline naturalness and pacing
The last train had already left, but she decided to walk anyway. The city was quieter than she remembered, and for the first time in weeks, she wasn't in a hurry.
Emotion, emphasis, and pauses
Wait — you're telling me it actually worked? After all that? I can't believe it. Honestly, I thought we'd lost the whole thing.
Decimals, percentages, version numbers
The API returned 3,481 results in 0.42 seconds, a 12 percent improvement over version 2.5. Latency at the 99th percentile dropped from 840 milliseconds to 610.
MiniMax
MiniMax is a Chinese AI lab whose speech and music models are widely used for multilingual voiceover and generative music.
www.minimax.io ↗