You deliver a 1920×1080 video, about 90–110 s, in which an avatar of whoever is presenting
greets the customers by name and walks through the real slides of a pitch deck. It should feel
like the sender recording a quick personal walkthrough, not an ad. The video is
workflow-pitch-deck-to-video's; this workflow adds getting to a finished deck for this
client, and the personal greeting.
Steps
1. Get to a finished deck
Work out which of three inputs the person brought, and say which one you're in:
- A. A finished deck for this client (PDF, PPTX, Keynote, images or a Canva link). Use it as is. Go to step 2.
- B. A deck template plus a client-details doc. Fill the template for this client.
- C. A brand guide plus a client-details doc. Build a new deck in that brand.
For a Canva deck, template or brand kit, follow workflow-sales-video-from-canva-deck, which
covers all three in Canva and hands back here at step 2.
The client-details doc
B and C both run on it. Read it and pull out: the client's name; the customers' names and how they're said; the presenter; what you heard from them (their needs, in their words); the scope (what you'll make, how many, what each one differs by); the reusable parts (a character, a fixed segment); the timeline; the pricing, including any discount for a case study; the date; and any images of theirs. List anything the deck needs that the doc doesn't say and ask for it in one message. Never make up prices, numbers, dates, quotes or claims; a field the doc doesn't cover is a question, not a guess.
B. Fill a template
- Copy the template; never edit the master. Name the copy " x proposal".
- Find every placeholder:
[bracketed]fields, sample names, dates and prices, and stock photos meant to be swapped. Read the speaker notes; a template often lists its fields there. - Fill each field from the doc. Keep the template's lengths: a field that's a short label stays short, so text doesn't wrap or collide. Rewrite one line rather than letting it overflow.
- Swap the photos for the client's own imagery when the doc supplies it. Otherwise leave the template's photos where they fit the client and say which ones you left.
- Drop slides the deal doesn't need, and clear any template notes out of the speaker notes.
- Check: no
[left anywhere, no text overflowing or overlapping, and the client's name spelled the same everywhere.
C. Build from a brand guide
- Take the brand guide's colours, type, logo and tone. If it has a slide template, start from that.
- Outline the standard proposal, one idea per slide: title ("Prepared for "), what we heard, approach, deliverables, timeline, pricing, and the sender's end card. Add or drop slides to fit the doc. Gate: the person approves the outline.
- Build the deck in a 4:3 frame if you can, since 4:3 leaves room for the presenter
(
workflow-pitch-deck-to-video, step 7). Use the brand's own type and colours, few words per slide, and one image per slide at most. Make it in whatever deck tool the session has; a deck that can be exported as images is all the video needs.
Gate (B and C): show every finished slide and get the deck approved before any voice or lip sync is paid for. A change to a slide after that costs a re-render of its span.
2. Before the video, ask who presents
Ask who presents (guide-present-with-an-avatar, its first question: never assume it's
the person you're talking to, never reuse an avatar unasked). Then, for this deal:
- The presenter's name as said in the greeting, and their role if it's mentioned.
- The customers' names and how to say them. Whisper writes unusual names differently; that's fine for the audio, but write lip-sync prompts from the script, never from the transcript.
- Which slides to use, and any house rules, such as no added on-screen text.
3. The video
Follow workflow-pitch-deck-to-video from its step 1, with this deal's picks:
- The presenter (
guide-present-with-an-avatar, an AI avatar of a real person): waist-up, centred, facing the camera, a plain dark backdrop; by default a library voice they pick (guide-cast-a-voice), saying it won't sound like them, or as an option their own cloned voice, which takes longer and asks more of them: their consent and a recording made aselevenlabs-clone-a-voicedescribes. Save both inrefs/. - The script: open with "Hi , hi ! It's from ,"
then what this is; say each slide to "you"; close warmly. In route B, a template's
speaker notes can be the first draft. Gate: the script, the presenter and the
cost, approved word for word in chat (recorded with
review_approveandanswered). - The voice:
eleven_v4, one tagged line per section, two takes each (seeds 11, 22), each checked against its lines (whisper-cli-transcribe-with-word-times, Check it). Gate: areview_chooseper section, its two takes as the options, all in the same turn; if the person says to use one take throughout, use one seed for every section. The sections join into one track (guide-present-with-an-avatar, Process step 2). - The lip sync: one gesture per chunk, a wave on the names and on the sign-off; about $0.094/s at list.
- Deliver
rev1/<Client>_pitch_<Names>.mp4and its 1280 px copy, and record the filled deck's link or file with the job's notes.
Choices this workflow makes
- Get to a finished, approved deck before anything is paid for. The deck is the script's backbone and the video's picture.
- Real people only: the presenter's own photos and voice, or a voice they picked.
- The personal greeting is the point: the customers' names in the first line, said right.
Dead ends
- Prices or claims filled in from memory or another client's deck: always from the details doc.
- A placeholder longer than the field it replaced: it wrapped and collided. Keep lengths close.
- Waiting on a device call over 60 s: it times out. Start it with
wait: false, then follow its id withtasks(wait: true, calls: [<id>], timeout_s: 50)(execsfor a program), again until it has ended.
Worked example
The first run, with an avatar and a voice the presenter already had: 100.6 s at 1920×1080, about $9.90 all in.


