Free: read existing captions on YouTube and Bilibili (5 reads/day for guests, unlimited for signed-in users), search, export. Free account: 30 min/week transcription, 10/week AI tasks. Single Pass: US$1.99 (1 transcription up to 180 minutes, 2 AI uses). Light Pack S: US$2.49 first purchase (was US$4
One-time payment plans: Starter $9.90 (500 credits), Pro $49.90 (2500 credits), Ultimate $99.90 (5000 credits). Average of 10 credits per second. All plans include high-quality generation, access to all major AI models, no watermark, and commercial use rights.
Key features
Read captions without sign-in
Search transcripts and jump to timestamps
Bilingual view for Chinese and English
Automatic speaker detection and labeling
AI summaries with chapter highlights
Transcribe videos without captions
Export quotes as TXT, SRT, or Markdown
AI translation between Chinese and English
Save reading history and personal labels
Upload local audio or video files
Multi-language support for lip synchronization across different languages and accents
512x512 high-resolution video output
Real-time processing with efficient architecture
Temporal consistency mechanisms for smooth lip movements
Whisper integration for precise audio feature extraction
End-to-end latent diffusion without intermediate motion representations
Low VRAM requirements for accessible scaling
Flexible deployment with Gradio App and CLI interface
What makes it different
Free subtitle reading without account for YouTube and Bilibili
One-click jump from transcript to video moment
No downloads or browser extensions needed
Metered allowances let you control costs
Bilingual transcripts with line-by-line comparison
Audio-conditioned latent diffusion without intermediate motion representations
Preserves original visual details and lighting in latent space
Language-agnostic processing works across different languages
Open source ecosystem with full access to code and checkpoints
Extensive research-backed algorithms for high-quality results