Inside The Machine

← All business recipes

B-01Blueprint · assembly sheet

Shorts cutter

Turn one long video into a handful of Shorts. Your machine does the listening and cutting. Claude picks the best moments.

Title blockbuild.ts

Part no.
B-01
Family
Content studio
Runs from
8 GBParts run one at a time
Status
Not tested yet
In
One long video you made (a file on your computer).
Out
3 to 5 vertical clips with captions, plus a title idea for each.
Tools
whisper.cppOllama
Note
Blueprint. Not run yet. The first real run is on a 128 GB Mac Studio from 10 Nov 2026.
1Claude's job

Claude does the few hard parts.

Planning, the hard writing and the final review. That takes few tokens.

Claude does
  • Reads one-line summaries of the top moments (not the whole transcript) and picks the 3 to 5 that stand alone.
  • Writes a hook line and a title for each pick.
  • Final check: does each clip make sense without the rest of the video?
Claude never sees

Claude never sees the video, the audio or the full transcript. It sees short summaries of the top-scored moments only.

2Local partsFig. 1 · Parts listmodels.json ·

Your machine does the bulk.

Find your memory. Each row names the model for each part. Free, private, on your computer.

The model for each part at each memory size. Parts run one at a time.speech.json · models.json ·
No.MemoryTranscriberDecider (Local Jev)Drafter
SZ-018 GB6 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.5 4Bneeds 5.8 GBRuns, but tightQwen3.5 4Bneeds 5.8 GBRuns, but tight
SZ-0216 GB12 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.5 0.8Bneeds 2.6 GBRuns wellGemma 4 12Bneeds 11.2 GBRuns, but tight
SZ-0324 GB18 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.5 4Bneeds 5.8 GBRuns wellGemma 4 12Bneeds 11.2 GBRuns well
SZ-0432 GB24 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.5 4Bneeds 5.8 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns, but tight
SZ-0548 GB36 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellGemma 4 12Bneeds 11.2 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns well
SZ-0664 GB48 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellGemma 4 12Bneeds 11.2 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns well
SZ-0796 GB72 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns well
SZ-08128 GB96 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns well
SZ-09192 GB144 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellQwen3.8-Flash-Next (125B-A6B)needs 140 GBRuns, but tight
SZ-10256 GB192 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellQwen3.8-Flash-Next (125B-A6B)needs 140 GBRuns well
SZ-11512 GB384 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellQwen3.8-Flash-Next (125B-A6B)needs 140 GBRuns well
Transcriber

Turns speech into text with timestamps.

How we pick it: The most accurate speech-to-text model that fits and runs in whisper.cpp (Mac, Windows and Linux). Accuracy is the Open ASR word error rate: lower is better.

Decider (Local Jev)

Answers typed questions about each item: pick one, give a score, or yes/no. It never writes.

How we pick it: The smartest chat model with an Ollama download that needs no more than a third of your usable memory. Smaller models answer sooner, and a decider only picks a label. If no model is that small, the drafter's model decides too.

Drafter

Writes the first draft of many small things: summaries, title options, reply drafts.

How we pick it: The smartest chat model that fits your usable memory and has an Ollama download (the same model the /do recipes install).

Fit labels

We count 75% of your memory as usable for AI. The rest is for the system and your apps. Runs well: the model fits in usable memory with at least 10% to spare. Runs, but tight: it fits, but less than 10% of usable memory is left. Close other apps first. Needs N GB+: it does not fit. N is the smallest memory size it fits in.

3Steps

9 steps.

Each step says who does it: you, Claude, your machine or a script.

  1. Youpick

    Pick one video you own

    A long video file on your computer. Your own work only.

  2. Your machineTranscribertranscribe

    Transcribe it

    Speech to text with a timestamp on every sentence. Runs on your machine.

  3. A scriptwindows

    Cut the text into moments

    A script splits the transcript into 20 to 60 second windows that start and end on a full sentence.

  4. Your machineDecider (Local Jev)score

    Score every moment

    Local Jev answers three typed questions per moment: how strong is the hook (score), does it make sense alone (yes/no), what is it about (pick one). Unsure answers are marked.

  5. Your machineDraftersummarise

    Sum up the top moments

    The drafter writes one line per top-scored moment. This is what Claude reads.

  6. Claudechoose

    Claude picks and titles

    Claude reads the one-liners, picks 3 to 5 moments and writes a hook line and title for each.

  7. A scriptcut

    Cut, crop and caption

    ffmpeg cuts each pick, crops it to 9:16 and burns in captions from the transcript.

  8. Youyours

    Make it yours

    Watch every clip. Fix the captions, re-record a hook in your own voice, cut what is weak. Post fewer, better clips.

  9. Youshare

    Share your run (optional)

    At the end, the script shows exactly what it would upload: your chip, memory, the models, how long each stage took and the token counts. No prompts, no outputs, no file names. Say yes and it goes to our review queue. Nothing is public until we approve it.

4Make it yours

The step only you can do.

Before you publish
  • YouTube does not pay for mass-produced, repetitive content (its "inauthentic content" rule). Every clip needs your own judgement and edits, not just the machine's cut.
  • Post the clips you would be proud of, not every clip the script makes.
  • If a clip shows realistic AI-made people, voices or events, YouTube asks you to turn on the "altered or synthetic content" label when you upload.
5Receiptsapproved runs

What a run costs.

Claude tokens for this recipe and for doing it all in Claude, local minutes and dollars. Only from runs a person has approved.

Receipts

No runs yet
Claude tokens, this recipe
not run yet
Claude tokens, all in Claude
not run yet
Local minutes
not run yet
Claude dollars (estimate)
not run yet
Not run yet

Not run yetBlueprints now, numbers later. We run every recipe on a 128 GB Mac Studio from 10 Nov 2026, then publish the receipts.

6Share your run

Share your run. Only if you want to.

At the end, the script shows exactly what it would upload and asks first. A person reviews every run before it shows here.

It sends
  • Your chip, memory, graphics card and operating system
  • The recipe and the models you used
  • How long each stage took
  • Token counts: Claude in and out, local in and out
  • How many items came out
  • Tool versions
  • A fingerprint (SHA-256) of the log and up to 15 cleaned log lines
  • A handle you pick (not your name or email)
It never sends
  • Your prompts or the model's answers
  • Your files, file names or folder paths
  • Emails, links, keys or IP addresses (the server rejects any upload that has one)
  • Your IP address in plain form: we keep a scrambled copy for rate limits only

Agents can share with the submit_run tool of https://insidethemachine.ai/mcp. Privacy

Agent view · text/markdown · or send Accept: text/markdown
# Blueprint: Shorts cutter

URL: https://insidethemachine.ai/build/shorts-cutter
Part: B-01. Family: Content studio. Status: Blueprint, not run yet.
Blueprint. Not run yet. The first real run is on a 128 GB Mac Studio from 10 Nov 2026.

Turn one long video into a handful of Shorts. Your machine does the listening and cutting. Claude picks the best moments.

- Input: One long video you made (a file on your computer).
- Output: 3 to 5 vertical clips with captions, plus a title idea for each.
- Runs from: 8 GB of memory.
- Tools: whisper-cpp (https://insidethemachine.ai/setups/whisper-cpp.md), ollama (https://insidethemachine.ai/setups/ollama.md)

## Claude's job

- Reads one-line summaries of the top moments (not the whole transcript) and picks the 3 to 5 that stand alone.
- Writes a hook line and a title for each pick.
- Final check: does each clip make sense without the rest of the video?

What Claude never sees: Claude never sees the video, the audio or the full transcript. It sees short summaries of the top-scored moments only.

## Local parts per memory size

Data: models.json 2026-10-15, speech.json 2026-10-15, images.json 2026-10-15.
| memory GB | Transcriber | Decider (Local Jev) | Drafter |
|---|---|---|---|
| 8 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.5 4B (needs 5.8 GB, runs, but tight) | Qwen3.5 4B (needs 5.8 GB, runs, but tight) |
| 16 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.5 0.8B (needs 2.6 GB, runs well) | Gemma 4 12B (needs 11.2 GB, runs, but tight) |
| 24 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.5 4B (needs 5.8 GB, runs well) | Gemma 4 12B (needs 11.2 GB, runs well) |
| 32 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.5 4B (needs 5.8 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs, but tight) |
| 48 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Gemma 4 12B (needs 11.2 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) |
| 64 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Gemma 4 12B (needs 11.2 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) |
| 96 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) |
| 128 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) |
| 192 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Qwen3.8-Flash-Next (125B-A6B) (needs 140 GB, runs, but tight) |
| 256 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Qwen3.8-Flash-Next (125B-A6B) (needs 140 GB, runs well) |
| 512 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Qwen3.8-Flash-Next (125B-A6B) (needs 140 GB, runs well) | 

How each part is picked:
- Transcriber: Turns speech into text with timestamps. Rule: The most accurate speech-to-text model that fits and runs in whisper.cpp (Mac, Windows and Linux). Accuracy is the Open ASR word error rate: lower is better. (speech.json)
- Decider (Local Jev): Answers typed questions about each item: pick one, give a score, or yes/no. It never writes. Rule: The smartest chat model with an Ollama download that needs no more than a third of your usable memory. Smaller models answer sooner, and a decider only picks a label. If no model is that small, the drafter's model decides too. (models.json)
- Drafter: Writes the first draft of many small things: summaries, title options, reply drafts. Rule: The smartest chat model that fits your usable memory and has an Ollama download (the same model the /do recipes install). (models.json)
- Fit: We count 75% of your memory as usable for AI. The rest is for the system and your apps. Runs well: the model fits in usable memory with at least 10% to spare. Runs, but tight: it fits, but less than 10% of usable memory is left. Close other apps first. Needs N GB+: it does not fit. N is the smallest memory size it fits in. Size unknown: we do not know how much memory it needs.

## Steps

1. **Pick one video you own** (You; stage id `pick`): A long video file on your computer. Your own work only.
2. **Transcribe it** (Your machine, Transcriber; stage id `transcribe`): Speech to text with a timestamp on every sentence. Runs on your machine.
3. **Cut the text into moments** (A script; stage id `windows`): A script splits the transcript into 20 to 60 second windows that start and end on a full sentence.
4. **Score every moment** (Your machine, Decider (Local Jev); stage id `score`): Local Jev answers three typed questions per moment: how strong is the hook (score), does it make sense alone (yes/no), what is it about (pick one). Unsure answers are marked.
5. **Sum up the top moments** (Your machine, Drafter; stage id `summarise`): The drafter writes one line per top-scored moment. This is what Claude reads.
6. **Claude picks and titles** (Claude; stage id `choose`): Claude reads the one-liners, picks 3 to 5 moments and writes a hook line and title for each.
7. **Cut, crop and caption** (A script; stage id `cut`): ffmpeg cuts each pick, crops it to 9:16 and burns in captions from the transcript.
8. **Make it yours** (You; stage id `yours`): Watch every clip. Fix the captions, re-record a hook in your own voice, cut what is weak. Post fewer, better clips.
9. **Share your run (optional)** (You; stage id `share`): At the end, the script shows exactly what it would upload: your chip, memory, the models, how long each stage took and the token counts. No prompts, no outputs, no file names. Say yes and it goes to our review queue. Nothing is public until we approve it.

## Make it yours

- YouTube does not pay for mass-produced, repetitive content (its "inauthentic content" rule). Every clip needs your own judgement and edits, not just the machine's cut.
- Post the clips you would be proud of, not every clip the script makes.
- If a clip shows realistic AI-made people, voices or events, YouTube asks you to turn on the "altered or synthetic content" label when you upload.

## Receipts

- Claude tokens, this recipe: not run yet
- Claude tokens, all in Claude: not run yet
- Local minutes: not run yet
- Claude dollars (estimate): not run yet

No approved runs yet. Blueprints now, numbers later. We run every recipe on a 128 GB Mac Studio from 10 Nov 2026, then publish the receipts.

## Share your run

Opt-in. The script shows exactly what it would upload and asks first. It sends: Your chip, memory, graphics card and operating system; The recipe and the models you used; How long each stage took; Token counts: Claude in and out, local in and out; How many items came out; Tool versions; A fingerprint (SHA-256) of the log and up to 15 cleaned log lines; A handle you pick (not your name or email). Never: Your prompts or the model's answers; Your files, file names or folder paths; Emails, links, keys or IP addresses (the server rejects any upload that has one); Your IP address in plain form: we keep a scrambled copy for rate limits only. Nothing is public until a person approves it. Agents can submit with the `submit_run` tool of https://insidethemachine.ai/mcp.

Privacy: https://insidethemachine.ai/privacy.md