Inside The Machine

← All business recipes

B-02Blueprint · assembly sheet

Videos → newsletter

Turn this week's videos into a newsletter draft. Your machine drafts each section. Claude writes the intro and does the final edit.

Title blockbuild.ts

Part no.
B-02
Family
Content studio
Runs from
8 GBParts run one at a time
Status
Not tested yet
In
This week's videos (files, or the caption files you already have).
Out
A newsletter draft: subject line, intro, one section per video.
Tools
whisper.cppOllama
Note
Blueprint. Not run yet. We will run it on our own newsletter, The Gap Report, 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
  • Writes the subject line and the intro: the hard writing.
  • Edits the sections the checker flagged.
  • Final review of the whole draft.
Claude never sees

Claude sees the drafted sections, not the full transcripts.

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.MemoryTranscriberDrafterDecider (Local Jev)
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 wellGemma 4 12Bneeds 11.2 GBRuns, but tightQwen3.5 0.8Bneeds 2.6 GBRuns well
SZ-0324 GB18 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellGemma 4 12Bneeds 11.2 GBRuns wellQwen3.5 4Bneeds 5.8 GBRuns well
SZ-0432 GB24 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns, but tightQwen3.5 4Bneeds 5.8 GBRuns well
SZ-0548 GB36 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellGemma 4 12Bneeds 11.2 GBRuns well
SZ-0664 GB48 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns wellGemma 4 12Bneeds 11.2 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-Flash-Next (125B-A6B)needs 140 GBRuns, but tightQwen3.8 27Bneeds 22.7 GBRuns well
SZ-10256 GB192 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.8-Flash-Next (125B-A6B)needs 140 GBRuns wellQwen3.8 27Bneeds 22.7 GBRuns well
SZ-11512 GB384 GB usableDistil-Whisper large-v3.5needs 2 GBRuns wellQwen3.8-Flash-Next (125B-A6B)needs 140 GBRuns wellQwen3.8 27Bneeds 22.7 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.

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).

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.

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

7 steps.

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

  1. Yougather

    Gather the week's videos

    Video files, or the caption files you already have (then skip the next step).

  2. Your machineTranscribertranscribe

    Transcribe each video

    Speech to text with timestamps. Runs on your machine.

  3. Your machineDrafterdraft

    Draft one section per video

    About 120 words, 3 key points and one quote with its timestamp.

  4. Your machineDecider (Local Jev)check

    Check every draft

    Local Jev asks: does it state a number that is not in the transcript (yes/no)? Is it in plain words (score)? Flags go to Claude.

  5. Claudeedit

    Claude writes the top and edits

    Subject line, intro, fixes to flagged sections, one final read.

  6. Youyours

    Make it yours

    Add your own take. Check every number against the video. Then paste it into your newsletter tool.

  7. 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
  • Readers subscribe to you. Add a paragraph only you could write.
  • Check every number and quote against the video before you send.
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: Videos → newsletter

URL: https://insidethemachine.ai/build/videos-to-newsletter
Part: B-02. Family: Content studio. Status: Blueprint, not run yet.
Blueprint. Not run yet. We will run it on our own newsletter, The Gap Report, from 10 Nov 2026.

Turn this week's videos into a newsletter draft. Your machine drafts each section. Claude writes the intro and does the final edit.

- Input: This week's videos (files, or the caption files you already have).
- Output: A newsletter draft: subject line, intro, one section per video.
- 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

- Writes the subject line and the intro: the hard writing.
- Edits the sections the checker flagged.
- Final review of the whole draft.

What Claude never sees: Claude sees the drafted sections, not the full transcripts.

## Local parts per memory size

Data: models.json 2026-10-15, speech.json 2026-10-15, images.json 2026-10-15.
| memory GB | Transcriber | Drafter | Decider (Local Jev) |
|---|---|---|---|
| 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) | Gemma 4 12B (needs 11.2 GB, runs, but tight) | Qwen3.5 0.8B (needs 2.6 GB, runs well) |
| 24 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Gemma 4 12B (needs 11.2 GB, runs well) | Qwen3.5 4B (needs 5.8 GB, runs well) |
| 32 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs, but tight) | Qwen3.5 4B (needs 5.8 GB, runs well) |
| 48 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Gemma 4 12B (needs 11.2 GB, runs well) |
| 64 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) | Gemma 4 12B (needs 11.2 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-Flash-Next (125B-A6B) (needs 140 GB, runs, but tight) | Qwen3.8 27B (needs 22.7 GB, runs well) |
| 256 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.8-Flash-Next (125B-A6B) (needs 140 GB, runs well) | Qwen3.8 27B (needs 22.7 GB, runs well) |
| 512 | Distil-Whisper large-v3.5 (needs 2 GB, runs well) | Qwen3.8-Flash-Next (125B-A6B) (needs 140 GB, runs well) | Qwen3.8 27B (needs 22.7 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)
- 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)
- 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)
- 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. **Gather the week's videos** (You; stage id `gather`): Video files, or the caption files you already have (then skip the next step).
2. **Transcribe each video** (Your machine, Transcriber; stage id `transcribe`): Speech to text with timestamps. Runs on your machine.
3. **Draft one section per video** (Your machine, Drafter; stage id `draft`): About 120 words, 3 key points and one quote with its timestamp.
4. **Check every draft** (Your machine, Decider (Local Jev); stage id `check`): Local Jev asks: does it state a number that is not in the transcript (yes/no)? Is it in plain words (score)? Flags go to Claude.
5. **Claude writes the top and edits** (Claude; stage id `edit`): Subject line, intro, fixes to flagged sections, one final read.
6. **Make it yours** (You; stage id `yours`): Add your own take. Check every number against the video. Then paste it into your newsletter tool.
7. **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

- Readers subscribe to you. Add a paragraph only you could write.
- Check every number and quote against the video before you send.

## 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