Skip to content
SereChat

Audio Models

ImagesVideosAudio

Create original music and audio compositions with state-of-the-art AI.

Ace Step
ACE-Step — create original music and audio from tags, lyrics, prompts, or audio reference.
ACE
Minimax Music 2.6
Prompt-based music generation with lyrics and lyric optimization controls.
Minimax
ElevenLabs Turbo v2.5
Ultra-fast text-to-speech generation with lifelike voices.
ElevenLabs
ElevenLabs v3
Expressive multilingual voice generation using ElevenLabs' premium v3 model.
ElevenLabs
Inworld TTS
Low-latency expressive speech synthesis optimized for gaming and virtual characters.
Inworld
Minimax Speech 02 HD
High-definition, extremely natural-sounding speech synthesis from MiniMax.
MiniMax