All tasks / Voice & audio

Sound effects

Models and apps that generate sound effects, ambience and foley from a description or match them to a video, including open models you can run yourself.

No public leaderboard covers this task yet, so its options are mapped but not ranked: every tile shows a dash instead of a tier. How we rank.

Rank by
Highlight

Models

The engines themselves. Use them through an API or inside the apps on the right.

Apps

Ready-made apps with a UI: sign in or install, then start.

Workflow platforms

Node and canvas tools that chain several models into one pipeline.

Cloud

Nothing tracked yet

Runtimes & APIs

Run open models on your own machine, or reach models and services through an API.

Cloud

Nothing tracked yet

Everything, in order

All sound effects options in quality order
TierNameApproachRunsRated byPriceSkill
– ComfyUI
Comfy Org
Workflow platformsLocalNo public result yetFreeadvanced
– WanGP (Wan2GP)
deepbeepmeep (community project)
AppsLocalNo public result yetFreeintermediate
– audio.cpp
0xShug0 (community)
Runtimes & APIsLocalNo public result yetFreeadvanced
– Adobe Firefly
Adobe
AppsCloudNo public result yet$9.99/mobeginner
– AudioX-Turbo
HKUST (HKUSTAudio) and NoizAI
ModelsLocalNo public result yetOpen weights—
– Beatoven.ai
Beatoven.ai
AppsCloudNo public result yetFree tier · $10/mobeginner
– ControlFoley
Xiaomi (xiaomi-research)
ModelsLocalNo public result yetOpen weights—
– Dasheng-AudioGen
Xiaomi (MiLM Plus / mispeech)
ModelsLocalNo public result yetOpen weights—
– ElevenLabs
ElevenLabs
AppsCloudNo public result yetFree tier · $6/mobeginner
– HunyuanVideo-Foley (XXL and XL)
Tencent Hunyuan
ModelsLocalNo public result yet~8 GB VRAM—
– Mirelo
Mirelo AI
AppsCloudNo public result yetFree tierbeginner
– Mirelo SFX 2.0
Mirelo AI
ModelsCloudNo public result yet——
– MMAudio (large_44k_v2)
UIUC and Sony AI
ModelsLocalNo public result yet~6 GB VRAM—
– MOSS-SoundEffect v2.0
OpenMOSS team and MOSI.AI
ModelsLocalNo public result yetOpen weights—
– OptimizerAI
OptimizerAI
AppsCloudNo public result yetFree tierbeginner
– PrismAudio
Alibaba (FunAudioLLM)
ModelsLocalNo public result yetOpen weights—
– SFX Engine
SFX Engine
AppsCloudNo public result yetFree tier · $10/mobeginner
– Sound Effects v2 (eleven_text_to_sound_v2)
ElevenLabs
ModelsCloudNo public result yet$0.12/min of audio—
– Stable Audio 3 Small SFX
Stability AI
ModelsLocalNo public result yetOpen weights—
– Woosh v1.0.1 (Flow, DFlow, VFlow, DVFlow)
Sony AI
ModelsLocalNo public result yetOpen weights—
– Wubble
Wubble AI
AppsCloudNo public result yetFree tier · $4.99/mobeginner

Benchmarks used