Place to run it · Video, Pictures, Voice and speech, Music and sound, Talking presenters, 3D

WaveSpeedAI

A pay-as-you-go service for running many makers' AI models: video (Seedance, Wan, Kling, Veo and others), images, speech and music, lip-sync avatars and 3D. You top up credit and pay per image or per second of video.

Go to WaveSpeedAI’s website

At a glance

Open or closed: Closed
Only usable through the maker's app or API
The service is closed; it hosts both open-weight and closed models.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Can I sell what I make?: Depends on the model you choose
Terms page could not be fetched (wavespeed.ai/terms and /terms-of-service returned errors), so output rights are unchecked.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Cost: Free option: $1 of free credit for eligible new accounts, no card needed; some premium models excluded
Plans below.
How you use it: Maker's own API, In your browser
Pricing page describes generating after topping up; API vs web playground split not confirmed on a page we read.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Skill needed: Technical
Our judgement: aimed mainly at developers.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Made by: WaveSpeedAI
Footer reads '© 2026 WAVESPEED'; no legal entity, address or country on the page. Terms page could not be fetched.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Status: Available
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

What you can make with it

A video, from a description (main use)
A video, by bringing a photo to life
A picture, from a description
A talking presenter, a talking version of a photo
A voice or speech, read my text aloud
Music and sound, a full song with vocals
A 3D object or scene, from a photo

text to videoimage to videotext to imageimage to imagetext to audioaudio to videoimage to 3D model

From the hosted model families on the pricing page (Seedance, Wan, Kling, Veo; Seedream, FLUX; speech, Mureka music; InfiniteTalk lip-sync; Tripo3D, Meshy). Also sells language-model access.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Plans and prices

Plan	Price	Includes
Wan 3.0 video (per second)	$0.05 per seconds of video	Starting price; resolution not stated.
Kling 3.0 Std video (per second)	$0.084 per seconds of video
Seedance 2.0 video (per second)	$0.12 per seconds of video
Seedream 5.0 Pro (per image)	$0.045 per image

Some plans are not listed here; see the source for the full list.

Example 'starting' list prices; actual cost depends on resolution, length and settings. '$' shown, USD assumed.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Rough cost of 5 seconds of 720p video: about $0.25 / £0.19 (estimate, worked out by Plainly, not a price the maker publishes). Wan 3.0 starting price $0.05/s x 5s = $0.25; page doesn't say this is 720p, so treat as a floor. GBP at 0.75.

Models you can run here

Seedance, Qwen-Image

Other options for “A video, from a description”

Adobe Express, Adobe Firefly, Adobe Premiere, Akool, Animoto, Arcads, Canva AI (Magic Studio), CapCut, Civitai, CogVideoX, ComfyUI, Creatify, DeeVid AI, DomoAI, Dreamina, Dzine, fal, Filmora, FlexClip, Fliki, Fotor, Genmo, getimg.ai, Google Flow

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.