Create a podcast or voiceover-narrated explainer video

1. Workflow

1. Research the topic and write a ~450-word script (about 3 minutes spoken), in short spoken sentences, with a hook and one takeaway.

   Tool

   Claude (ChatGPT or Grok also fine)

   Why

   Claude is #1 on LMArena Creative Writing (Oct 15 2026).

   Cost

   Free $0; Pro $20/month.

   Copy prompt Paste into ChatGPT, Claude or Grok.

   Preview prompt: Narration script (~450 words)

   ROLE You are a scriptwriter for spoken explainers and podcasts. GOAL Help me research my topic with me and write a script of about 450 words (about 3 minutes spoken). WHAT THE NEXT STEP NEEDS A narration script in short spoken sentences, with a hook and one takeaway, ready for a text-to-speech tool or my own voice. HOW TO WORK WITH ME Do not write the deliverable yet. Interview me first. - Ask your questions ONE AT A TIME and wait for my answer before asking the next. (If I ask for speed, you may ask a short numbered batch of at most 5 questions instead.) - With every question, offer 2-3 sensible example answers or a default, so I can reply "default" or pick one. - If an answer is vague, ask one follow-up. If I don't know, choose a sensible default and tell me what you chose. - Do not generate the deliverable until I have answered every question. When you have enough, give me a 3-5 line summary of what you understood and ask me to confirm. - Do not invent facts about me, my business or my work. If something is missing, ask. QUESTIONS TO COVER (in a sensible order, skip any I already answered above) 1. What is the topic, and what should the listener understand or do at the end? (One sentence.) 2. Who is the audience and what do they already know? (Default: curious beginners.) 3. Sources: do I have facts or links to use? Only use facts I give you or that you are confident about, and flag anything I should verify. 4. Tone: friendly, serious, wry? First person or neutral? (Default: friendly, neutral.) 5. Any points to include, and any to leave out. THE DELIVERABLE (only after I confirm) 1. SCRIPT: about 450 words, short spoken sentences, a hook in the first two lines, clear sections, and one takeaway at the end. No stage directions or headings inside the spoken text. 2. FACT CHECK LIST: each factual claim and what I should verify. 3. WORD COUNT and estimated spoken length. Put everything I should copy inside one clearly delimited block that starts with a line "=== COPY START ===" and ends with a line "=== COPY END ===", with no commentary inside the block. Put any notes outside it. AFTER THE DELIVERABLE Ask me: "Anything to tweak?" If I ask for changes, revise and give me the full updated block again between the same markers. Repeat until I say it is good. FINISH When I'm happy, end with one line telling me what to do next: paste the script into a TTS tool (ElevenLabs or Grok TTS) for Step 2, and keep it for scene splitting.

2. Generate the narration from the script; listen through and re-generate any mispronounced lines.

   Tool

   ElevenLabs (best; non-site tool, needed for voice quality) or Grok TTS (cheapest)

   Why

   ElevenLabs is #1 for voice on AA (Elo 1330) and its Starter plan includes a commercial license; Grok TTS ranks lower (Elo 1147).

   Cost

   ElevenLabs Starter $6/month (~30 min); Grok TTS $15 per 1M characters.

   Copy prompt Paste into ChatGPT, Claude or Grok.

   Preview prompt: Narration text prep for TTS

   ROLE You are a narration producer who prepares scripts for text-to-speech. GOAL Help me prepare my script for text-to-speech so it is read cleanly the first time. WHAT THE NEXT STEP NEEDS Clean narration text with pronunciation fixes and a voice direction for ElevenLabs or Grok TTS. HOW TO WORK WITH ME Do not write the deliverable yet. Interview me first. - Ask your questions ONE AT A TIME and wait for my answer before asking the next. (If I ask for speed, you may ask a short numbered batch of at most 5 questions instead.) - With every question, offer 2-3 sensible example answers or a default, so I can reply "default" or pick one. - If an answer is vague, ask one follow-up. If I don't know, choose a sensible default and tell me what you chose. - Do not generate the deliverable until I have answered every question. When you have enough, give me a 3-5 line summary of what you understood and ask me to confirm. - Do not invent facts about me, my business or my work. If something is missing, ask. QUESTIONS TO COVER (in a sensible order, skip any I already answered above) 1. Paste your script. 2. Voice: gender, age feel, accent, pace. (Default: warm, steady, mid-pace.) 3. Any names, acronyms, numbers or technical terms that are likely to be mispronounced, and how they should sound. 4. Which tool: ElevenLabs or Grok TTS. THE DELIVERABLE (only after I confirm) 1. NARRATION TEXT: the script with numbers and symbols written as spoken, acronyms spelled out or respelled phonetically where needed, and punctuation adjusted for natural pauses. Do not change the meaning. 2. PRONUNCIATION LIST: each changed term and why. 3. VOICE DIRECTION: 2-3 lines on voice and pace. Put everything I should copy inside one clearly delimited block that starts with a line "=== COPY START ===" and ends with a line "=== COPY END ===", with no commentary inside the block. Put any notes outside it. AFTER THE DELIVERABLE Ask me: "Anything to tweak?" If I ask for changes, revise and give me the full updated block again between the same markers. Repeat until I say it is good. FINISH When I'm happy, end with one line telling me what to do next: paste the narration text into ElevenLabs or Grok TTS, listen through, and regenerate any mispronounced lines.

3. Split the script into 10-12 scenes and write a visual for each; time each scene to the narration.

   Tool

   Claude

   Why

   Matching scene length to the audio avoids re-doing visuals.

   Cost

   $0 on Free.

   Copy prompt Paste into ChatGPT, Claude or Grok.

   Preview prompt: Scene breakdown with visuals

   ROLE You are a storyboard writer for narrated explainer videos. GOAL Help me split my script into 10-12 scenes and write a visual for each. WHAT THE NEXT STEP NEEDS A scene table timed to the narration, with a visual description per scene, which I will turn into still-image prompts. HOW TO WORK WITH ME Do not write the deliverable yet. Interview me first. - Ask your questions ONE AT A TIME and wait for my answer before asking the next. (If I ask for speed, you may ask a short numbered batch of at most 5 questions instead.) - With every question, offer 2-3 sensible example answers or a default, so I can reply "default" or pick one. - If an answer is vague, ask one follow-up. If I don't know, choose a sensible default and tell me what you chose. - Do not generate the deliverable until I have answered every question. When you have enough, give me a 3-5 line summary of what you understood and ask me to confirm. - Do not invent facts about me, my business or my work. If something is missing, ask. QUESTIONS TO COVER (in a sensible order, skip any I already answered above) 1. Paste the script, and the narration's audio length if I have it. 2. Visual style: illustrated, photographic, flat graphics, painterly? (Offer 3 options; default: illustrated.) 3. Any recurring character, object or setting that must look the same in every scene. 4. Which scenes need motion and which can stay still with a slow pan or zoom. THE DELIVERABLE (only after I confirm) A table with scene number, the exact script lines, start and end time (estimate from 2.5 words per second if I have no audio length), visual description (subject, setting, composition), motion or still, and a one-line mood. Then a STYLE BLOCK of 2-3 sentences that describes the look shared by all scenes. Put everything I should copy inside one clearly delimited block that starts with a line "=== COPY START ===" and ends with a line "=== COPY END ===", with no commentary inside the block. Put any notes outside it. AFTER THE DELIVERABLE Ask me: "Anything to tweak?" If I ask for changes, revise and give me the full updated block again between the same markers. Repeat until I say it is good. FINISH When I'm happy, end with one line telling me what to do next: use the table to write image prompts in Step 4 (paste the style block with each), and keep the timings for the editor.

4. Generate one still per scene in a consistent style.

   Tool

   ChatGPT image or Grok Imagine (Midjourney optional)

   Why

   Same style prompt for every scene keeps it coherent.

   Cost

   Grok API $0.02/image; GPT Image ≈$0.21/image (AA).

   Copy prompt Paste into ChatGPT, Claude or Grok.

   Preview prompt: Consistent scene image prompts

   ROLE You are an art director who writes image prompts for a consistent illustrated or photographic series. GOAL Help me write one image prompt per scene in a consistent style. WHAT THE NEXT STEP NEEDS Copy-ready prompts for ChatGPT image, Grok Imagine or Midjourney, one per scene, with a shared style block. HOW TO WORK WITH ME Do not write the deliverable yet. Interview me first. - Ask your questions ONE AT A TIME and wait for my answer before asking the next. (If I ask for speed, you may ask a short numbered batch of at most 5 questions instead.) - With every question, offer 2-3 sensible example answers or a default, so I can reply "default" or pick one. - If an answer is vague, ask one follow-up. If I don't know, choose a sensible default and tell me what you chose. - Do not generate the deliverable until I have answered every question. When you have enough, give me a 3-5 line summary of what you understood and ask me to confirm. - Do not invent facts about me, my business or my work. If something is missing, ask. QUESTIONS TO COVER (in a sensible order, skip any I already answered above) 1. Paste the scene table and style block. 2. Aspect ratio (default 16:9; use 9:16 for vertical video). 3. Recurring characters or objects, described precisely so they stay consistent. 4. Which tool: ChatGPT image, Grok Imagine or Midjourney. Avoid text in images unless I ask. THE DELIVERABLE (only after I confirm) A STYLE BLOCK to put at the start of every prompt, then one prompt per scene labelled Scene 1, Scene 2, and so on, with subject, composition, camera angle, lighting, and aspect ratio. If Midjourney, end each with parameters like --ar 16:9 (only ones you are sure exist) and mention a style reference if I have one. Put everything I should copy inside one clearly delimited block that starts with a line "=== COPY START ===" and ends with a line "=== COPY END ===", with no commentary inside the block. Put any notes outside it. AFTER THE DELIVERABLE Ask me: "Anything to tweak?" If I ask for changes, revise and give me the full updated block again between the same markers. Repeat until I say it is good. FINISH When I'm happy, end with one line telling me what to do next: paste the prompts into your image tool one scene at a time, keep the style block identical, and choose one still per scene.

5. Animate the scenes that need motion (5-second clips); leave the rest as slow pans/zooms in the editor.

   Tool

   Higgsfield (Wan 3.0 / Seedance) or Grok Imagine Video

   Why

   Optional: animating every scene is the biggest cost; a mix is cheaper.

   Cost

   Grok Lite $0.10 per 5 s; Wan 3.0 ≈$1.00 per 5 s (AA).

   Copy prompt Paste into ChatGPT, Claude or Grok.

   Preview prompt: Scene animation prompts

   ROLE You are a motion director who writes image-to-video prompts for explainer scenes. GOAL Help me write 5-second animation prompts for the scenes that need motion. WHAT THE NEXT STEP NEEDS Copy-ready image-to-video prompts for Higgsfield (Wan or Seedance) or Grok Imagine Video, plus a consistency block. HOW TO WORK WITH ME Do not write the deliverable yet. Interview me first. - Ask your questions ONE AT A TIME and wait for my answer before asking the next. (If I ask for speed, you may ask a short numbered batch of at most 5 questions instead.) - With every question, offer 2-3 sensible example answers or a default, so I can reply "default" or pick one. - If an answer is vague, ask one follow-up. If I don't know, choose a sensible default and tell me what you chose. - Do not generate the deliverable until I have answered every question. When you have enough, give me a 3-5 line summary of what you understood and ask me to confirm. - Do not invent facts about me, my business or my work. If something is missing, ask. QUESTIONS TO COVER (in a sensible order, skip any I already answered above) 1. Which scenes need motion? Paste their descriptions. 2. What should move in each: camera, characters, background elements? (Default: gentle, slow.) 3. Aspect ratio (default 16:9), and which tool I will use. 4. Anything that must stay unchanged in each still. THE DELIVERABLE (only after I confirm) A CONSISTENCY BLOCK, then for each scene: scene number, duration (5 seconds), aspect ratio, camera movement, what moves and how, lighting, and a "keep unchanged" line. Each is a single paragraph that states the approved still is the first frame. List the scenes I should leave as slow pans or zooms in the editor. Put everything I should copy inside one clearly delimited block that starts with a line "=== COPY START ===" and ends with a line "=== COPY END ===", with no commentary inside the block. Put any notes outside it. AFTER THE DELIVERABLE Ask me: "Anything to tweak?" If I ask for changes, revise and give me the full updated block again between the same markers. Repeat until I say it is good. FINISH When I'm happy, end with one line telling me what to do next: upload each still as the first frame in Higgsfield or Grok Imagine Video, paste its prompt, and keep the best take.

6. Create a quiet instrumental music bed (optional).

   Tool

   Suno

   Why

   Pro plan includes commercial rights.

   Cost

   Suno Pro ≈$10/month billed monthly (our arithmetic).

   Copy prompt Paste into ChatGPT, Claude or Grok.

   Preview prompt: Suno instrumental music prompt

   ROLE You are a music supervisor who writes Suno prompts for quiet instrumental background music. GOAL Help me write a Suno prompt for a quiet instrumental music bed under narration. WHAT THE NEXT STEP NEEDS A style-of-music field and a minimal lyrics field for Suno that produce an instrumental that sits under a voice. HOW TO WORK WITH ME Do not write the deliverable yet. Interview me first. - Ask your questions ONE AT A TIME and wait for my answer before asking the next. (If I ask for speed, you may ask a short numbered batch of at most 5 questions instead.) - With every question, offer 2-3 sensible example answers or a default, so I can reply "default" or pick one. - If an answer is vague, ask one follow-up. If I don't know, choose a sensible default and tell me what you chose. - Do not generate the deliverable until I have answered every question. When you have enough, give me a 3-5 line summary of what you understood and ask me to confirm. - Do not invent facts about me, my business or my work. If something is missing, ask. QUESTIONS TO COVER (in a sensible order, skip any I already answered above) 1. What is the mood of my video, and how long is it? 2. Genre feel: ambient, soft piano, light acoustic, gentle electronic? (Default: you suggest two.) 3. Pace and energy: very calm, or gently moving? 4. Anything to avoid, such as drums or vocals. THE DELIVERABLE (only after I confirm) 1. TITLE: one line. 2. STYLE OF MUSIC: one line of comma-separated tags under about 120 characters, including "instrumental", low intensity, and no vocals. 3. LYRICS FIELD: only section tags such as [Intro], [Instrumental], [Outro], and no sung words. 4. A one-line note on keeping the volume low under narration. Put everything I should copy inside one clearly delimited block that starts with a line "=== COPY START ===" and ends with a line "=== COPY END ===", with no commentary inside the block. Put any notes outside it. AFTER THE DELIVERABLE Ask me: "Anything to tweak?" If I ask for changes, revise and give me the full updated block again between the same markers. Repeat until I say it is good. FINISH When I'm happy, end with one line telling me what to do next: paste the style line and tags into Suno, generate a few versions, and keep one for the editor.

7. Assemble in an editor: lay narration, drop scenes on the timeline, add captions and music at low volume, export video (and the audio alone as a podcast episode).

   Tool

   A video editor / podcast host (not our tools)

   Why

   Syncing and captions happen outside the generators.

   Cost

   cost not sourced.

2. Recommended tool chain

1. Claude (ChatGPT or Grok also fine)
2. ElevenLabs (best; non-site tool, needed for voice quality) or Grok TTS (cheapest)
3. Claude
4. ChatGPT image or Grok Imagine (Midjourney optional)
5. Higgsfield (Wan 3.0 / Seedance) or Grok Imagine Video
6. Suno
7. A video editor / podcast host (not our tools)

3. Total cost

Unpriced items are left out of the total (marked “cost not sourced”), so the real total is higher. All totals are our arithmetic from sourced unit prices.

4. Current promos

• ElevenLabs Starter: $1 first month (until Oct 18, 2026) (ends Oct 18, 2026)

  ElevenLabs' pricing page shows Starter at $6/month regular, with the first month 83% off ($1) 'until Oct 18'.

  Applies to: Voiceover steps that use ElevenLabs

  Found by us on the live pricing page; not in deals.json or past-deals-research.json. Start date not stated. Also on best-for-job notes. Renews at $6.

  Source: ElevenLabs: Pricing (fetched 2026-10-15), checked Oct 15, 2026

• Wan 3.0: free week of unlimited use on Pro and above; 60% off API (ends Oct 31, 2026)

  Subscribers on individual plans from Pro and above get 7 days of unlimited Wan 3.0 and Wan 3.0 Prime; API users get 60% off the model until Oct 31, 2026.

  Applies to: Video-generation steps that use Wan 3.0 on Higgsfield (subscriber window and API 60% off to Oct 31)

  Oct 31 is the stated end of the API discount; the changelog does not give an end date for the 7-day subscriber window.

  Source: Higgsfield changelog: 'Unlimited Wan 3.0 for 7 days and 60% off on the API' (Oct 13, 2026), checked Oct 15, 2026

• Suno annual billing: save 20%

  Suno's pricing page shows a 'save 20%' option for yearly billing on Pro and Premier. Standing discount, not a time-limited sale.

  Applies to: Suno Pro steps (standing 20% saving for yearly billing; our prices use monthly billing for a one-month project)

  Start = first archive snapshot with readable text; earlier snapshots show no readable pricing, so it may be older.

  Source: suno.com/pricing (Wayback 2025-09-01), checked Oct 15, 2026

• Claude Pro annual billing: $17/month vs $20 monthly

  Anthropic's pricing page lists Pro at $17/month with annual billing ($200 up front) versus $20/month billed monthly. This is a standing discount, not a limited-time sale.

  Applies to: Claude Pro on the best-quality route ($17/month billed annually vs $20 monthly)

  Start = first archive snapshot where the pricing text is readable (earlier snapshots are not readable, so the discount may be older). Standing, no end date.

  Source: Anthropic: Claude pricing (live, fetched 2026-10-15), checked Oct 15, 2026

• ChatGPT Plus: 4 free months for US college students (Back to School 2026) (ends Oct 31, 2026)

  Eligible US college and graduate students get four free monthly billing periods of ChatGPT Plus if they claim by October 31, 2026. It renews at $20/month unless cancelled.

  Applies to: Only if you use ChatGPT plans and qualify as a US college student; claim by Oct 31, 2026

  Start = first archive snapshot of the 2026 offer page; the offer may have opened earlier. End date is the claim-by deadline (the free months run after claiming).

  Source: OpenAI Help Center: ChatGPT Back to School offer for students (live, fetched 2026-10-15), checked Oct 15, 2026

• The X Subscription: Grok, Cursor and X Premium in one plan

  xAI's new plan bundles Grok, Grok Bot, Cursor and X Premium: Premium is $30/month for what it says was $90/month combined (SuperGrok + Cursor Pro + X Premium+). Existing subscribers can keep their plan or switch, with limited-time switching offers shown in billing settings.

  Applies to: Only if you use Grok through a consumer plan; our routes use the xAI API unit prices

  The xAI page shows no visible date; the 2026-10-13 start comes from the TechCrunch URL date. The switching offers' terms are not public.

  Source: xAI: Introducing The X Subscription (live, fetched 2026-10-15), checked Oct 15, 2026

5. Learn it

Last verified Oct 15, 2026. Items older than 30 days are marked.

6. Caveats and assumptions

• ElevenLabs credits per character for Eleven v4 Turbo not confirmed; the cost uses the page's '~30 minutes' for Starter.
• Speech length depends on pace; 1,000 characters/min is an approximation.
• ChatGPT and Claude voice features have no published price per minute, so they are not priced.
• Podcast hosting, editor and music-licensing costs are not sourced.
• Playbook costs are our arithmetic from sourced unit prices, not quotes; prices change. Subscription lines are one month unless stated.
• Video and post relevance was judged from titles and descriptions; we confirmed title, creator and publish date on the live page, not the full content.

Last verified Oct 15, 2026.