Create a 12-second rap duet with AI vocals and music from your photos
Free AI text to speech and voice generator with public voice auditions, consent-based cloning, and downloadable audio
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Paid
Freemium
Pricing
Lite: $4.90 one-time for 1 video valid for 365 days. Pro: $8.90 one-time for 2 videos valid for 365 days. Ultra: $19.90 one-time for 5 videos valid for 365 days. No automatic renewal.
Not given
Key features
Four stage environments: recording studio, orange booth, street cypher, and luxury lobby
Four performance styles: friendly duet, birthday shout-out, couple duet, and friendly rap battle
Support for English and Mandarin Chinese languages
Multiple video formats: 9:16 portrait, 1:1 square, and 16:9 landscape
12-second, 768P video output with native AI-generated audio
Pre-generation text safety screening with Waffo Prompt Screening
Review and download functionality before sharing videos
Support for two portraits or one shared photo upload
300+ public voice profiles to audition across multiple languages
Natural text to speech with punctuation and emphasis control
Consent-based voice cloning for private speaker models
Voice design to create synthetic speakers from written descriptions
Searchable multilingual voice catalog with 4 language groups
Generation history for comparing and retrieving previous takes
Downloadable audio files in browser
Support for up to 1,000 characters per conversion on paid plans
Browser-based production workspace with no installation required
Unified credit system for text to speech, voice design, and cloning
What makes it different
Original AI-generated lyrics and music created for each video, not pre-recorded or copied
No subscription required; one-time purchase video packs with 365-day validity
Powered by MiniMax H3 video generation model with native AI audio
Straightforward workflow with four steps: upload photos, choose stage, select performance, add personal details
Iterative workflow that keeps scripts editable while auditing voice options
Permission-gated private voice cloning with rights confirmation before model creation
Generation history to support revisions and comparisons instead of relying on memory
Script-first workflow that treats writing problems as audio problems to solve early
Support for multiple languages in one workspace without switching tools