Quote the narration at one moment of a generated clip
Proof frames
Tool calls
transcribe
Arguments
{
"source": "$CLIP"
}
Result
{
"ok": true,
"data": {
"status": "in_progress",
"requested_model_size": "tiny",
"requested_model_cached": false,
"transcription_status": "started",
"retry_after_seconds": 15,
"transcription_message": "The tiny transcription started in the background. About 0% done (estimate): 0 s elapsed of roughly 10 s. Retry in about 15 seconds.",
"elapsed_sec": 0,
"estimated_total_sec": 10,
"estimated_percent": 0
}
}
transcribe
Arguments
{
"source": "$CLIP"
}
Result
{
"ok": true,
"data": {
"status": "in_progress",
"requested_model_size": "tiny",
"requested_model_cached": false,
"transcription_status": "in_progress",
"retry_after_seconds": 15,
"transcription_message": "A transcription for this video is already running. About 30% done (estimate): 3 s elapsed of roughly 10 s. Retry in about 15 seconds.",
"elapsed_sec": 3,
"estimated_total_sec": 10,
"estimated_percent": 30
}
}
transcribe
Arguments
{
"source": "$CLIP"
}
Result
{
"ok": true,
"data": {
"source_path": "~/hill/gallery/repo/cards/quote-synthetic/clip.mp4",
"language": "en",
"duration_sec": 17,
"segment_count": 4,
"segments": [
{
"id": 1,
"start_sec": 0,
"end_sec": 4,
"text": "The counter and the corner shows the seconds.",
"start_timecode": "00:00:00.000",
"end_timecode": "00:00:04.000",
"confidence": 0.99
},
{
"id": 2,
"start_sec": 4,
"end_sec": 8,
"text": "The speaker's mouth moves while the voice talks.",
"start_timecode": "00:00:04.000",
"end_timecode": "00:00:08.000",
"confidence": 0.99
},
{
"id": 3,
"start_sec": 8,
"end_sec": 12.28,
"text": "Nothing in this clip comes from a camera.",
"start_timecode": "00:00:08.000",
"end_timecode": "00:00:12.280",
"confidence": 0.99
},
{
"id": 4,
"start_sec": 12.28,
"end_sec": 14.28,
"text": "This is a generated test clip.",
"start_timecode": "00:00:12.280",
"end_timecode": "00:00:14.280",
"confidence": 0.99
}
],
"has_speech": true,
"notice": "Note: Non-speech audio (music, sound effects, alarms) is NOT transcribed.",
"confidence": 0.99,
"uncertainty": "Whisper confidence is a no_speech_prob proxy; transcript content and alignment remain model-dependent."
}
}
Question and answer
- Question
- What exactly is said starting about 4 seconds into this clip?
- Answer
- The transcript has the speaker saying "The speaker's mouth moves while the voice talks." from 4.0 seconds.
How it was checked
- Truth from
- constructed
- Fixed at
Taken from the script captions our generator wrote for the source: the caption line at 21.00 to 23.37 s in the source, which is 4.00 to 6.37 s in the clip. The clip is the source from 17.00 to 34.00 s, cut with no edit. The line was picked by a seeded rule (seed from the card id) from 2 eligible caption lines of 8 to 25 words, 2 to 10 s long, starting at least 4 s in, ending 0.5 s before the window does, with at least two words of 5 or more letters, and with no sound tag, music mark, dialogue dash or speaker label; the required phrases are the first 3 of those words in the line. No picture or sound was changed, and no tool was asked for the answer.
The check is the script line our generator spoke, and the 17-second clip was cut from the source with no edit, so a word that transcribe hears differently counts as a miss.
Try it yourself
Use agentic-video to transcribe my video, then quote the exact words said starting about 4 seconds in. Use my own file.
- Get the .mcpb file and open it in Claude Desktop.
- Or:
pip install agentic-video
Clip and licence
- Licence
- generated
Generated for the gallery; no third-party material.