3 个模型
该系列包含 2 个提供商
MiniMax
MiniMax Speech 2.8 is an async text-to-speech API with HD and turbo quality modes, preset voices, custom MiniMax voice_id support, emotion control, pronunciation dictionaries, and multilingual output settings.
MiniMax
MiniMax Voice creates reusable custom voice IDs from text-described voice design or a single public reference audio clip, then returns preview audio for validation.
suno
Latest Suno text-to-music model that returns two polished songs per call with faster queues and richer vocals.