Autocaption
Availablefictions-ai · fictions-ai/autocaption
Tasks using this model
Input contract
- Required inputs
- video_file_input
- Optional inputs
- font, color, kerning, opacity, MaxChars, fontsize, translate, output_video, stroke_color, stroke_width, right_to_left, subs_position, highlight_color, output_transcript, transcript_file_input
- Output
- video, transcript (uri-array)
- Submission
- Pinned community version
Provider billing
No standard page rate; calibrated 2026-10-06 from measured runs at the community fleet rate (≈$0.000927/s hardware): 4-5 s speech videos → predict 1.0-2.3 s ≈ $0.001-0.0022 per run, scaling with audio length.
Provider-side unit, for reference only. This site charges a fixed credit tier per execution — the price shown at quoting time is the price paid.
Contract notes
translate means translate INTO English only — never advertised as multi-language captioning. Supports uploading an edited transcript to re-run the burn-in (transcript_file_input — not exposed in the v2 form yet). MEASURED 2026-10-06 (batch F runs report): the output is an ARRAY — output.mp4 (captioned, keeps audio) then transcript_out.json (word-level timestamps); Chinese speech transcribes correctly but the ASR emits TRADITIONAL variants of some characters (今天天氣很好… from a simplified zh_CN utterance) — the Chinese copy stays honest about this; English output follows the speech length (4.11 s video from a 4.11 s speech source). Cost scales with audio length (predict 1.0 s zh / 2.3 s en for 4-5 s sources). Enabled 2026-10-06: batch F deployed-app E2E green (batch-f-e2e report).
Status
This model is catalogued and its contract is locked, but real executions have not passed acceptance yet. Nothing on this page should be read as a claim that it is usable today.
- License
- Community model; license not yet reviewed.
- Last verified
- 2026-10-05