Translate subtitles
to Chinese

How it works for Chinese

Upload an English .srt or .vtt file, or a season as a zip. Cues travel to the model in batches of 32 so a sentence that spans two cues is translated as one thought. Every Chinese cue then passes thirteen structural checks; whatever fails goes back with the exact complaint attached, and an editor pass sweeps the whole file for register and idiom. You download the subtitles and a quality report, and the upload is deleted.

What the Chinese profile checks

• Simplified characters and Mainland usage by instruction, with full-width punctuation (，。？！).
• Line width is 32 columns at two per glyph; reading speed is 9 characters per second.
• Chinese output is expected to be shorter than its English source (a ratio up to 0.9). Cues that are only a sound label are exempt, because they come back identical by construction and would otherwise be flagged on every file.
• Scored with chrF rather than chrF++, as for Japanese. The gold set covers 10% of an episode, too thin to publish a baseline.

Sound labels, from the table

Labels for the deaf and hard of hearing are resolved from a fixed Chinesetable before the model sees the text, so they are never invented. Three entries, exactly as the table renders them:

[LAUGHS]

[笑]

[DOOR CLOSES]

[关门声]

[PHONE RINGS]

[电话铃响]

Is Chinese measured?

A human reference exists for Chinese but covers only 10% of an episode, which is too thin to publish a number from. The same thirteen structural checks run on every Chinese cue regardless, and the quality report in your download lists what they found.

Price and time

One credit translates about 20,000 characters of dialogue, roughly a 25-minute episode; a feature film is about three. Credits are $1.25 each in packs, the first episode is free, and there is no subscription. An episode takes a few minutes; you get an email when it is ready.