AI models for video, image, audio and voice

Kling v3, Seedance 2.5, Hailuo, FLUX.2, Nano Banana 2, OmniHuman, ElevenLabs, Demucs and 70+ more AI models behind one prompt box and one balance.

Video models

Seedance 2.5 — Best quality · native audio
Kling O3 Pro — Balanced · multi-shot
MiniMax H3 Max — Best value · up to 15 s
Gemini Omni Flash — Google · Veo’s successor · up to 4K
Kling v3 Pro — Cinematic · native audio
Kling v3 Standard — Cinematic · value tier
Seedance 2.0 — Audio · first + last frame
Seedance 2.0 Fast — Fast drafts · audio
Seedance 1.5 Pro — Budget · start+end frames
Happy Horse 1.1 — Native audio · lip-sync
Kling 2.5 Turbo Pro — Fast · start+end frames
Kling O1 — Reference-to-video · restyle
Hailuo 2.3 Pro — 1080p · smooth motion
Wan 2.7 — Open source · up to 1080p
Grok Imagine — Fast · text/image → video
LTX 2.3 — i2v · up to 2160p
LongCat — Budget text → video
OmniHuman 1.5 — Talking head · full body
Kling Avatar — Talking head · best value
Sync 3 Avatar — Talking head · any art style
InfiniTalk — Talking head · pick a length
PixVerse Lipsync — Lip sync · cheapest
Kling O3 Edit — Restyle · keeps audio
Luma Ray 3.2 — Restyle & reframe · premium
HeyGen Translate — Dubbing · 13 languages
ElevenLabs Dubbing — Dubbing · keeps the voice

Image models

Seedream 5.0 Pro — Flagship · reference edits
FLUX.2 Pro — Studio photoreal
Nano Banana 2 — Smart edits · up to 4K
Nano Banana 2.1 — Newest Google · up to 4K
FLUX 3 — BFL flagship · up to 4K
Nano Banana Pro — Premium edits · up to 4K
GPT Image 2 — Precise edits
Ideogram V4 — Best text · posters & logos
Seedream 4.5 — All-round · up to 4K
FLUX.1 Schnell — Fastest drafts

Audio and voice models

MiniMax Music — Style + lyrics → song
CassetteAI Music — Text → music · up to 3 min
Stable Audio — High-fidelity music
ElevenLabs Voiceover — Natural TTS
ElevenLabs SFX — Sound effects
MMAudio — Match sound to a clip
Demucs — Stem splitting · pennies

What each model costs

Seedance 2.5: from 154 tokens ($1.54) per clip
Kling O3 Pro: from 62 tokens ($0.62) per clip
MiniMax H3 Max: from 47 tokens ($0.47) per clip
Gemini Omni Flash: from 19 tokens ($0.19) per clip
Kling v3 Pro: from 101 tokens ($1.01) per clip
Kling v3 Standard: from 77 tokens ($0.77) per clip
Seedance 2.0: from 102 tokens ($1.02) per clip
Seedance 2.0 Fast: from 83 tokens ($0.83) per clip
Seedance 1.5 Pro: from 14 tokens ($0.14) per clip
Happy Horse 1.1: from 77 tokens ($0.77) per clip
Kling 2.5 Turbo Pro: from 65 tokens ($0.65) per clip
Kling O1: from 62 tokens ($0.62) per clip
Hailuo 2.3 Pro: from 89 tokens ($0.89) per clip
Wan 2.7: from 90 tokens ($0.90) per clip
Grok Imagine: from 38 tokens ($0.38) per clip
LTX 2.3: from 87 tokens ($0.87) per clip
LongCat: from 23 tokens ($0.23) per clip
Seedream 5.0 Pro: from 14 tokens ($0.14) per image
FLUX.2 Pro: from 6 tokens ($0.06) per image
Nano Banana 2: from 12 tokens ($0.12) per image
Nano Banana 2.1: from 10 tokens ($0.10) per image
FLUX 3: from 6 tokens ($0.06) per image
Nano Banana Pro: from 29 tokens ($0.29) per image
GPT Image 2: from 2 tokens ($0.02) per image
Ideogram V4: from 2 tokens ($0.02) per image
Seedream 4.5: from 8 tokens ($0.08) per image
FLUX.1 Schnell: from 1 tokens ($0.01) per image
MiniMax Music: from 6 tokens ($0.06) per track
CassetteAI Music: from 2 tokens ($0.02) per track
Stable Audio: from 3 tokens ($0.03) per track
ElevenLabs Voiceover: about 3 tokens ($0.03) per 250 characters
ElevenLabs SFX: from 1 tokens ($0.01) per clip
MMAudio (match to clip): from 1 tokens ($0.01) per clip
OmniHuman 1.5: about 272 tokens ($2.72) per 10 s of audio
Kling Avatar: about 139 tokens ($1.39) per 10 s of audio
Sync 3 Avatar: about 228 tokens ($2.28) per 10 s of audio
InfiniTalk: from 169 tokens ($1.69) per clip
PixVerse Lipsync: about 73 tokens ($0.73) per 10 s of source video
Kling O3 · Edit: about 285 tokens ($2.85) per 10 s of source video
Luma Ray 3.2 · Restyle: from 128 tokens ($1.28) per clip
HeyGen Translate: about 174 tokens ($1.74) per 10 s of source video
ElevenLabs Dubbing: about 107 tokens ($1.07) per 10 s of source video
Demucs · Split stems: about 2 tokens ($0.02) per 10 s of audio

Prices come from the live catalog. Dollar amounts are at $0.0100 per token; top-up packs and subscriptions give you tokens for less. The exact price is shown before you generate, and a failed generation is refunded.