🤖 Model
minimax/music-15
Generate complete songs with vocals and accompaniment from a text style prompt and structured lyrics. Provide a prompt (...
← Back to search
singing-voice-generation AI Models
Found 11 models (showing 1-11)
🤖 Model
minimax/music-1.5
Generate songs with vocals and accompaniment from lyrics and a text prompt. Optionally learn style from a 5-30s referenc...
🤖 Model
minimax/music-01
Generate up to 60 seconds of music with vocals from lyrics and a reference track. Condition on a reference song to learn...
🤖 Model
lucataco/ace-step
Generates music from text prompts and optional lyrics. Supports various musical styles including synth-pop, electronic,...
🤖 Model
jourdelune/diffrhythm
Generate full-length songs with vocals from timestamped lyrics. Accepts lyric text in LRC-style [mm:ss.xx] timestamps, w...
🤖 Model 📝 → 🔊
lucataco/step-audio-tts-3b
Generate speech audio from text. Support multilingual TTS (Chinese and English), emotional expression and voice style co...
🤖 Model
fofr/yue
Generate music from lyrics and genre descriptions using the YuE-s1-7B model. Takes structured lyrics with segment tags (...
🤖 Model
minimax/music-2.5
Generate full-length songs with vocals from lyrics and an optional style prompt. Provide lyrics (up to 3,500 characters)...
🤖 Model
meta-innovation/heart_mula
Generate complete songs with lyrics from text descriptions and style tags. Takes lyrics input with structured sections l...
🤖 Model 📝 → 📝
2feet6inches/cog-hyped-bot
Generates Japanese hip-hop style lyrics from any input phrase or topic. Takes a text topic as input and produces rap lyr...
🤖 Model
sakemin/musicgen-newjeans-vocals
Generates music from text prompts using MusicGen trained on NewJeans songs with vocals. Accepts text descriptions of des...