Soul-AILab/SoulX-Podcast-1.7B
Text-to-Speech • 2B • Updated • 228 • 239
Audio Tasks
-
-
bosonai/higgs-tts-2-3b-base
Text-to-Speech • 6B • Updated • 566k • 693 -
Vocal Isolator
🗣37Isolate vocals from audio files
-
nvidia/personaplex-7b-v1
Audio-to-Audio • 8B • Updated • 212k • • 2.67k -
FlashLabs/Chroma-4B
Any-to-Any • 6B • Updated • 60 • 382 -
Qwen3-TTS Demo
🎙2.16kGenerate speech from text with voice design, cloning, or presets
-
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Text-to-Speech • 2B • Updated • 2.25M • 1.89k -
ACE-Step/acestep-v15-base
Text-to-Audio • 2B • Updated • 2.33k • 67 -
kugelaudio/kugelaudio-0-open
Text-to-Speech • 9B • Updated • 1.97k • 195 -
OpenMOSS-Team/MOSS-TTS
Text-to-Speech • 8B • Updated • 9.24k • 422 -
YatharthS/LavaSR
Audio-to-Audio • Updated • 881 • 84 -
PatnaikAshish/kokoclone
Text-to-Speech • Updated • 25 • 33 -
kyutai/hibiki-zero-3b-pytorch-bf16
Audio-to-Audio • Updated • 1.03k • 57 -
openbmb/MiniCPM-o-4_5
Any-to-Any • 9B • Updated • 1M • 1.47k -
Fish Audio S2 Pro
🐟178Zero GPU Text-to-Speech using Fish Audio S2 Pro
-
neuphonic/neutts-nano-spanish
Text-to-Speech • 0.2B • Updated • 1.72k • 12 -
nvidia/RE-USE
Audio-to-Audio • 9.61M • Updated • 20.6k • 97 -
CohereLabs/cohere-transcribe-03-2026
Automatic Speech Recognition • 2B • Updated • 690k • • 1.08k -
k2-fsa/OmniVoice
Text-to-Speech • 0.6B • Updated • 915k • 1.28k -
mispeech/midashenglm-7b-1021-fp8
Audio-Text-to-Text • 8B • Updated • 18 • 5 -
openbmb/VoxCPM2
Text-to-Speech • 2B • Updated • 430k • 1.54k -
ACE-Step/acestep-v15-xl-turbo
Text-to-Audio • 5B • Updated • 4.24k • 202 -
ScenemaAI/scenema-audio
Text-to-Speech • Updated • 105 • 147 -
fishaudio/s2-pro
Text-to-Speech • 5B • Updated • 512k • 1.26k -
ResembleAI/Dramabox
Text-to-Speech • Updated • 221 • 315 -
kyutai/moshika-rl-seamless
Audio-to-Audio • 8B • Updated • 145 • 31 -
ViiTorVoice
📚124Clone, Edit, and Generate Human-Like Speech
-
laion/voiceclap-large-v2
Feature Extraction • 9B • Updated • 8.52k • 12 -
nyralabs/CrisperWhisper2.0_large
Automatic Speech Recognition • 2B • Updated • 26k • 103 -
nineninesix/diamond-1.0
Audio-to-Audio • Updated • 80