Home / Task guides / Convert video to text and extract scripts
Top pick: Tongyi Tingwu. It is directly accessible in mainland China and transcribes uploaded audio and video; during the new-user trial, 2 hours can be uploaded per day. For video being edited in Jianying, get the text through subtitle recognition; for English video, consider Otter.
Updated 2026-10-27
Audio and video transcription with automatic meeting minutes
Accepts audio and video file uploads, and transcripts can be exported.
PricingDuring the new-user trial: 2 hours of audio/video uploads and 48 hours of live recording per day Official pricing (opens in a new tab)
Transcribes video with local models and exports text or subtitle files.
Proofread the text right after subtitle recognition, suited to video you are editing.
PricingBasic editing is free; some features such as subtitle recognition and HD export require membership Third-party source (opens in a new tab)
Suited to English content; the free plan includes 300 minutes per month.
PricingFree plan: 300 transcription minutes per month, up to 30 minutes per session; Pro USD 16.99 per user per month billed monthly Official pricing (opens in a new tab)
| Tongyi Tingwu | Buzz | Jianying (CapCut China) | Otter | |
|---|---|---|---|---|
| China access | Accessible in China | — | Accessible in China | Accessible in China |
| Pricing | During the new-user trial: 2 hours of audio/video uploads and 48 hours of live recording per day | — | Basic editing is free; some features such as subtitle recognition and HD export require membership | Free plan: 300 transcription minutes per month, up to 30 minutes per session; Pro USD 16.99 per user per month billed monthly |
| Chinese interface | Supports Chinese | — | Supports Chinese | Homepage in English |