MiniMax is a high-definition text-to-speech model

The number of channels of the generated audio. 1: mono, 2: stereo.

Default audio URL to load in the player before generation

Supports English text normalization, which improves performance in number-reading scenarios.

Enhance the ability to recognize specified languages and dialects.

Speech pitch. Range: -12 to 12, where 0 is normal pitch.

Text to convert to speech. Maximum 10000 characters. Use <#x#> between words to control pause duration (0.01-99.99s).

Speech speed. Range: 0.5-2.0, where 1.0 is normal speed.

Desired voice ID. Use a trained voice ID or one of the system voice IDs.

Speech volume. Range: 0.1-10.0, where 1.0 is normal volume.

Generate natural, multi-voice audio with MiniMax Speech-02 HD on GPU. Try instant TTS in the playground or deploy via API.

Minimax Speech 02 HD