Add a subtitle track viewers can switch off
Add talk.srt to bunny.mp4 as a subtitle track that viewers can turn on and off. Do not re-encode the video. Save it as soft.mp4.
The task
The reference answer shows the job can be done with deft. It is not an agent run.
deft video add-subtitles bunny.mp4 --subtitles talk.srt --soft -o soft.mp4
Input
1 00:00:00,500 --> 00:00:03,000 A quiet morning in the forest 2 00:00:03,500 --> 00:00:06,000 The big bunny wakes up 3 00:00:06,500 --> 00:00:09,500 Something is about to happen
Reference output
How a result is judged (1 check)
- media: file = "soft.mp4", has_subtitles = true, video_codec = "h264"
Runs
CodexWithout deftPassed2026-11-07
- Time
- 10s
- New tokens
- 4.8k
- Total input
- 41.7k
- Output tokens
- 0.3k
- Commands
- 2
- Failed
- 0
Trace
I’ll inspect the two files and available media tools, then mux the subtitle as a selectable track while copying the video stream unchanged.
pwd && ls -l talk.srt bunny.mp4 && command -v ffmpeg && ffmpeg -version | head -n 1output
-rw-r--r--@ 1 user staff 969201 Nov 5 21:11 bunny.mp4 -rw-r--r--@ 1 user staff 180 Nov 5 18:26 talk.srt /opt/homebrew/bin/ffmpeg ffmpeg version 7.1.1 Copyright (c) 2000-2025 the FFmpeg developers
ffmpeg -i bunny.mp4 -i talk.srt -map 0 -map 1:0 -c copy -c:s mov_text -metadata:s:s:0 language=eng soft.mp4output
ffmpeg version 7.1.1 Copyright (c) 2000-2025 the FFmpeg developers built with Apple clang version 15.0.0 (clang-1500.1.0.2.5) configuration: --prefix=/opt/homebrew/Cellar/ffmpeg/7.1.1_1 --enable-shared --enable-pthreads --enable-version3 --cc=clang --host-cflags= --host-ldflags='-Wl,-ld_classic' --enable-ffplay --enable-gnutls --enable-gpl --enable-libaom --enable-libaribb24 --enable-libbluray --enable-libdav1d --enable-libharfbuzz --enable-libjxl --enable-libmp3lame --enable-libopus --enable-librav1e --enable-librist --enable-librubberband --enable-libsnappy --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libtesseract --enable-libtheora --enable-libvidstab --enable-libvmaf --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libxvid --enable-lzma --enable-libfontconfig --enable-libfreetype --enable-frei0r --enable-libass --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libspeex --enable-libsoxr --enable-libzmq --enable-libzimg --disable-libjack --disable-indev=jack --enable-videotoolbox --enable-audiotoolbox --enable-neon libavutil 59. 39.100 / 59. 39.100 libavcodec 61. 19.101 / 61. 19.101 libavformat 61. 7.100 / 61. 7.100 libavdevice 61. 3.100 / 61. 3.100 libavfilter 10. 4.100 / 10. 4.100 libswscale 8. 3.100 / 8. 3.100 libswresample 5. 3.100 / 5. 3.100 libpostproc 58. 3.100 / 58. 3.100 Input #0, mov,mp4,m4a,3 … 2250 more characters
Created [soft.mp4](soft.mp4) with `talk.srt` as a selectable subtitle track. The video was stream-copied without re-encoding.
Output
CodexWith deft, skill installedPassedRead the skillUsed deft2026-11-07
- Time
- 17s
- New tokens
- 8.4k
- Total input
- 74.0k
- Output tokens
- 0.6k
- Commands
- 4
- Failed
- 0
Trace
I’ll inspect the two files and the local media instructions, then mux the SRT as a selectable subtitle track while copying the video stream unchanged.
cat .agents/skills/deft/SKILL.md 2>/dev/null || cat .agents/skills/deft/SKILL.md 2>/dev/null; pwd; rg --files -g 'bunny.mp4' -g 'talk.srt' -g 'AGENTS.md' -g 'SKILL.md'output
--- name: deft description: "Use deft instead of writing a script for file jobs: PDF merge/split/compress/watermark, image resize/convert/compress, video and audio trim/convert/compress, spreadsheets, Markdown to PDF/HTML, and YouTube downloads and subtitles." --- # deft One local command for file jobs. Prefer it over writing Python or shell scripts. Syntax: `deft <group> <command> [inputs] [-o output] [--options]` Groups: - `pdf`: Merge, split, compress, encrypt, forms, OCR, compare, convert - `image`: Resize, crop, convert, compress, filters, montage, OCR - `video`: Trim, crop, speed, convert, compress, GIF, frames (ffmpeg) - `audio`: Convert, trim, merge, fade, speed, tag, normalize (ffmpeg) - `doc`: Word/ODT/RTF: to text, Markdown, HTML, PDF; find and replace - `slides`: PowerPoint: extract text, Markdown outline, PDF handout - `data`: JSON/YAML/TOML/XML: convert, query with jq syntax, merge, diff - `sheet`: Excel/CSV/ODS tables: filter, sort, join, pivot, convert - `md`: Markdown to PDF, HTML, Word, EPUB; table of contents - `html`: HTML to Markdown, text, Word, PDF; screenshots - `epub`: E-books: info, to text, Markdown and PDF - `email`: EML files: headers, text, attachments - `contact`: VCF address books: to and from CSV - `calendar`: ICS calendars: to and from CSV - `gps`: GPX and KML tracks: convert, distance and time - `youtube`: Info, download, audio, subtitles, thumbnail (yt-dlp) - `file`: Any file: hash, duplicates, batch rename, base64, encoding - `qr`: Cre … 748 more characters
The local `deft` skill applies to video and subtitle file jobs, so I’m using its video tooling and checking the mux options before creating the output.
deft video --help; command -v ffmpeg; ls -lh bunny.mp4 talk.srtoutput
deft video - commands (input -> output) info video -> report Duration, size, frame rate, codecs add-audio video -> video Replace or mix the soundtrack: --audio song.mp3 add-subtitles video -> video Add subtitles: burned into the picture, or --soft chunk video -> video... Cut into equal parts: --length 10:00 compress video -> mp4 Smaller file: --level, --target-size, --max-height convert video|gif -> video Change container and codec: --to mp4|webm|mov|mkv crop video -> video Cut a region: --box or --aspect 1:1 download url -> video Save a video: --resolution 720p, --to mp4|webm|mkv [net] extract-audio video -> audio Save the soundtrack: --to mp3|m4a|wav|flac|ogg extract-subtitles video -> srt|vtt Save an embedded subtitle track: --to srt|vtt fade video -> video Fade: --fade-in 1 --fade-out 2 frames video -> png|jpg... Save frames as images: --fps 1 or --at 0:05,0:10 from-images image... -> video Slideshow: --duration, --fps, --audio merge video... -> mp4 Join videos; --transition fades mute video -> video Remove the audio track pad video -> video Fit into a frame with bars: --size 1080x1920 repeat video -> video Repeat a video: --count 3 plays it three times resize vid … 1027 more characters
deft video add-subtitles --helpoutput
deft video add-subtitles - Add subtitles: burned into the picture, or --soft Usage: deft video add-subtitles <video>... [-o <video|dir>] [options] In: video (each handled separately) Out: video (default <name>.subtitled.<ext>) Burned subtitles use this machine's fonts, so Chinese and other scripts work. --soft adds a track the viewer can turn off (no re-encoding). Options: --subtitles <path> An .srt or .vtt file (required) --soft Add a selectable track instead of burning in --font-size <number> Text size in pixels (default: 5% of the height) --color <color> Text color (default white) --position <position> bottom or top (default bottom) --font <text> Font family Common: -o --force --dry-run --json -j (deft help common) Examples: deft video add-subtitles clip.mp4 --subtitles talk.srt -o subbed.mp4 deft video add-subtitles clip.mp4 --subtitles zh.srt -o zh.mp4 deft video add-subtitles clip.mp4 --subtitles talk.vtt --soft -o soft.mp4 Result fields: cues Needs: ffmpeg, ffprobe
deft video add-subtitles bunny.mp4 --subtitles talk.srt --soft -o soft.mp4 --jsonoutput
{"v":1,"ok":true,"op":"video.add-subtitles","items":[{"ok":true,"inputs":["bunny.mp4"],"outputs":[{"path":"soft.mp4","format":"mp4","bytes":969961}],"facts":{"cues":3},"warnings":[]}],"elapsed_ms":70}Created [soft.mp4](soft.mp4) with a selectable subtitle track. The video was not re-encoded.
Output
CodexWith deft, skill as AGENTS.mdPassed2026-11-05
- Time
- 16s
- New tokens
- 11.5k
- Total input
- 79.8k
- Output tokens
- 0.5k
- Commands
- 4
- Failed
- 0
Trace
I’ll inspect the two files and use `deft` or a direct container mux operation to add a selectable subtitle track while copying the video stream unchanged.
pwd && ls -l talk.srt bunny.mp4 && deftoutput
-rw-r--r--@ 1 user staff 969201 Nov 4 19:32 bunny.mp4 -rw-r--r--@ 1 user staff 180 Nov 4 21:40 talk.srt deft 0.1.0 - local file toolkit. Usage: deft <group> <command> [inputs] [-o output] Groups: pdf Merge, split, pages, compress, watermark, number, PDF <-> images/text image Resize, crop, convert, compress PNG/JPEG/WebP/AVIF/GIF/TIFF/SVG video Trim, convert, compress, GIF, frames, extract audio (ffmpeg) audio Convert, trim, merge, normalize, compress (ffmpeg) subtitle SRT/VTT: convert, shift timing, burn into video, extract sheet Excel/CSV/ODS/JSON tables: convert, extract ranges, merge md Markdown to PDF and HTML archive zip/tar/tar.gz: create, extract, list youtube Info, download, audio, subtitles, thumbnail (yt-dlp; other sites work too) Any file: convert <in>... -o <out> Any-to-any by extension, e.g. deft convert a.png -o a.pdf info <file>... Type, size, pages, dimensions, duration find <words> Search commands by intent Next: deft <group> | deft <group> <command> --help | deft help common Other: schema, engine, skill, mcp, doctor. Results are one line; add --json for structure.
deft subtitle --help && deft video --helpoutput
deft subtitle - commands (input -> output) info subtitle -> report Number of lines, start and end time burn video -> video Add subtitles: burned into the picture, or --soft convert subtitle -> text Change format: --to srt|vtt|txt|md from-video video -> srt|vtt Save an embedded subtitle track: --to srt|vtt shift subtitle -> subtitle Move all timing: --by 2.5 (later) or --by -1 (earlier) More: deft subtitle <command> --help deft video - commands (input -> output) info video -> report Duration, size, frame rate, codecs add-subtitles video -> video Add subtitles: burned into the picture, or --soft compress video -> mp4 Smaller file: --level, --target-size, --max-height convert video -> video Change container and codec: --to mp4|webm|mov|mkv download url -> video Save a video: --resolution 720p, --to mp4|webm|mkv [net] extract-audio video -> audio Save the soundtrack: --to mp3|m4a|wav|flac|ogg extract-subtitles video -> srt|vtt Save an embedded subtitle track: --to srt|vtt frames video -> png|jpg... Save frames as images: --fps 1 or --at 0:05,0:10 merge video... -> mp4 Join videos in order (sizes are matched to the first) mute video -> video Remove the audio track resize video -> video Scale: --size 1280x, x720, 50% rotate vi … 343 more characters
deft video add-subtitles --helpoutput
deft video add-subtitles - Add subtitles: burned into the picture, or --soft Same as: deft subtitle burn Usage: deft video add-subtitles <video>... [-o <video|dir>] [options] In: video (each handled separately) Out: video (default <name>.subtitled.<ext>) Burned subtitles use this machine's fonts, so Chinese and other scripts work. --soft adds a track the viewer can turn off (no re-encoding). Options: --subtitles <path> An .srt or .vtt file (required) --soft Add a selectable track instead of burning in --font-size <number> Text size in pixels (default: 5% of the height) --color <color> Text color (default white) --position <position> bottom or top (default bottom) --font <text> Font family Common: -o --force --dry-run --json -j (deft help common) Examples: deft video add-subtitles clip.mp4 --subtitles talk.srt -o subbed.mp4 deft subtitle burn clip.mp4 --subtitles zh.srt -o zh.mp4 deft video add-subtitles clip.mp4 --subtitles talk.vtt --soft -o soft.mp4 Result fields: cues Needs: ffmpeg, ffprobe
deft video add-subtitles bunny.mp4 --subtitles talk.srt --soft -o soft.mp4 && deft video info soft.mp4output
ok video.add-subtitles bunny.mp4 -> soft.mp4 3 lines, soft track 0.10s ok video.info soft.mp4 0:10, 1280x720 bitrate=775968 duration=10.0 fps=30.0 height=720 video_codec=h264 width=1280
Created [soft.mp4](soft.mp4) with `talk.srt` as a selectable subtitle track. The video remains H.264; `deft` added the track without re-encoding.
Output
Its files were not kept in this run. The last line of the trace is its own report.
Claude Opus 5.5Without deftPassed2026-11-07
- Time
- 13s
- New tokens
- 9.5k
- Total input
- 43.0k
- Output tokens
- 0.7k
- Commands
- 0
- Failed
- 0
Trace
Output
Claude Opus 5.5With deft, skill installedPassedRead the skillUsed deft2026-11-07
- Time
- 17s
- New tokens
- 10.8k
- Total input
- 76.1k
- Output tokens
- 0.8k
- Commands
- 0
- Failed
- 0
Trace
Output
--- name: deft description: "Use deft first for any simple, direct operation on local files, whatever the type: convert, read, extract, edit, compress, merge, split, compare or inspect. Try it before writing a script or one-liner. If unsure, run deft find; if it says no command does this, use another tool. Not for programming work: to read, write or change source code, skip it." --- # deft One local command for file jobs. Prefer it over writing Python or shell scripts. Syntax: `deft <group> <command> [inputs] [-o output] [--options]` Groups: - `pdf`: Merge, split, compress, encrypt, forms, OCR, compare, convert - `image`: Resize, crop, convert, compress, adjust, montage, OCR - `video`: Trim, merge, convert, compress, subtitles, GIF, frames (ffmpeg) - `audio`: Convert, trim, normalize, denoise, cut silence (ffmpeg) - `doc`: Word/ODT/RTF: to text, Markdown, HTML, PDF; find and replace - `slides`: PowerPoint: extract text, Markdown outline - `sheet`: Excel/CSV/ODS tables: SQL query, pivot, merge, split, convert - `json`: JSON: convert, format, merge, diff, validate - `toml`: TOML: convert, format, merge, diff, validate - `xml`: XML: convert, format, merge, diff, validate - `yaml`: YAML: convert, format, merge, diff, validate - `md`: Markdown to PDF, HTML, Word, EPUB; table of contents - `html`: HTML to Markdown, text, Word and PDF - `epub`: E-books: info, to text, Markdown and PDF - `gps`: GPX and KML tracks: convert, distance and time - `qr`: Create QR codes and barcodes; read QR codes How to use it: 1. Run `deft <group>` to list commands, or `deft find "<what you want>"` to search. If it says `no command does this`, use another tool. 2. Run `deft <group> <command> --help` for options and examples. 3. `deft convert <in> -o <out.ext>` converts between formats by extension. 4. Results are one line starting with `ok`, `partial` or `error`; add `--json` to parse them. Errors include a `hint:` with the fix. Inputs are never overwritten; pass `--force` or `--in-place` to allow it. Globs and directories work as inputs; several inputs run in parallel. If `deft` is not installed, ask the user, then follow https://github.com/firstprayer/deft/blob/main/docs/INSTALL.md
Claude CodeWithout deftNot run yet
Claude CodeWith deftNot run yet