AI video generator with text, image, reference or document input, up to 30 seconds with native audio at 1080P
Browser-based voice cloning and text-to-speech platform supporting 83 languages
Stage
Startup
Not given
Founded
2026
Not given
Based in
AU
Not given
Pricing model
Paid
Paid
Pricing
Not given
Entry plan: 450 credits for $9; Standard plan: 950 credits for $19; Professional plan: 2,450 credits for $49; Flagship plan: 4,950 credits for $99. Voice cloning costs 100 credits per voice. Text-to-speech costs 1,500 credits per 1,000,000 UTF-8 bytes. Transcription costs 0.15 credits per second. Vo
Key features
Image to video from first frame, last frame, or both
Reference to video with up to 10 images, 5 video clips and 5 audio tracks
Document or web page to video conversion
Video editing and rewriting without regeneration
Output up to 30 seconds in a single pass at 30 fps
Three resolution tiers: 480P, 720P, 1080P
Audio including speech, effects and music generated natively
Failed generations automatically return credits
Commercial use rights included on all paid plans
Voice cloning from audio samples
Text-to-speech in 83 languages
Streaming output with ~90ms latency
Speech-to-text transcription
Voice design from text descriptions
200,000+ pre-built voice library
Emotion tags for speech generation
No GPU or software installation required
Key and audio encryption protection
Commercial usage rights for owned or consented voices
What makes it different
Only interface showing Alibaba's API task receipts with every generated video for full transparency
Document and web page to video, unique to Wan 3.0 and not offered by competing models
All input modes and full 1080P resolution included on lowest paid plan at $12.90 per month
Twice the single-pass length and three times the prompt characters versus nearest competitor
Independent third-party interface with transparent pricing and all specs linked to Alibaba's official documentation
Pay-as-you-go with no monthly subscription or expiring credits
Fast voice cloning from 10-second audio samples
Support for 83 languages with language-independent models
wan-3.run
Resona