“Looking for Make.com expert for AI podcast automation (ElevenLabs, HeyGen, Podsqueeze)”

Hire a Pro Hire Help
1

Hi, I’m looking for an experienced Make.com expert to build an automated workflow for an AI podcast / video show.

Tech stack:

  • Make.com

  • Google Drive + Google Sheets

  • ElevenLabs (voice)

  • HeyGen (avatars/video)

  • Podsqueeze (podcast show notes, titles, descriptions)

What I want automated

Workflow 1 – Pre‑production (script → audio/video assets)

  • Watch a Google Drive folder for a new episode script (Google Doc or text file).

  • Parse the script into segments: Narrator, Marcus, Gigi.

  • For each line:

    • Send text to ElevenLabs to generate voiceovers for Narrator, Marcus, and Gigi using specific voices.

    • Save audio files into an organized Google Drive structure with clear naming (EP number, character, line number).

  • Create or update a Google Sheet log with each episode, segment timing, and file paths for the audio (and later video) assets.

Workflow 2 – Post‑production (audio → show notes & metadata)

  • When a final episode audio file is added to a Google Drive folder, automatically send it to Podsqueeze.

  • Retrieve and save: title ideas, episode description, show notes, timestamps, social captions, etc.

  • Write this data into a Google Doc and update the tracking Google Sheet with links and key metadata.

Phase 2 – HeyGen video automation (separate budget)

  • Take the Marcus and Gigi dialogue lines and their ElevenLabs audio files.

  • Call the HeyGen API to render avatar videos for each line with:

    • Correct avatar (Marcus or Gigi)

    • The matching audio file

    • “More expression / motion” turned on

    • A custom motion prompt that fits the dialogue emotion (e.g., “confident but slightly annoyed podcast host,” “playful but serious during disagreement”).

  • Save each video clip to Google Drive with consistent naming and write the paths back into the Google Sheet so they can be dropped into a CapCut timeline later.

Deliverables

  • Working Make.com scenarios for:

    • Workflow 1 (script → segmented audio, logging to Sheet)

    • Workflow 2 (final audio → Podsqueeze → Docs/Sheets)

  • For Phase 2: a separate scenario (or extension) that creates HeyGen clips and updates the Sheet.

  • Clear documentation or loom-style walkthrough so I can run and adjust the scenarios.

What I’m looking for

  • Proven experience with Make.com (please share examples of multi‑step automations you’ve built).

  • Comfortable working with APIs and webhooks (ElevenLabs, HeyGen, Podsqueeze, Google).

  • Good communication and ability to suggest improvements to the flow.

Budget:

  • Phase 1 (Workflows 1 & 2): approx. $250–$500 fixed.

  • Phase 2 (HeyGen integration): additional budget to be agreed based on scope.

If this fits your skills, please reply with:

  1. A short note on how you’d approach this.

  2. Links or screenshots of similar automations you’ve built.

  3. Your estimated timeline and price for Phase 1 (and ballpark for Phase 2).

1 Like
3

Hi macdrazy,
This is a very well-structured brief — I like how clearly you’ve defined both phases.
I’ve built multi-step Make.com systems involving HTTP modules, AI integrations, file handling, structured logging, and scenario orchestration, so this fits my workflow style very well.

How I’d approach Phase 1

Workflow 1 – Script → Segmented Audio

• Watch Google Drive for new script file
• Parse roles (Narrator / Marcus / Gigi) using structured text splitting + iterator
• Route lines per character
• Call ElevenLabs via HTTP (or native module if preferred) with mapped voice IDs
• Save audio files using consistent naming convention
• Store file paths, segment order, and metadata inside Google Sheets
• Add error handling + retry logic for failed API calls

Everything would be modular so adding more characters later is easy.

Workflow 2 – Final Audio → Podsqueeze → Metadata

• Trigger on final audio upload
• Send file to Podsqueeze API
• Parse returned JSON (titles, descriptions, timestamps, captions)
• Generate structured Google Doc
• Update master tracking Sheet with:
Drive links

Metadata

Episode status

Phase 2 – HeyGen

For the HeyGen rendering:

• Iterate Marcus/Gigi dialogue rows from Sheet
• Call HeyGen API with:
Correct avatar ID
Corresponding ElevenLabs audio
Expression flag enabled
Emotion prompt dynamically mapped from script tone
• Save video outputs to Drive
• Write paths back into the Sheet for editorial use

I’d also include throttling control since HeyGen rendering queues can require async status polling.

Similar Work

Recently built:

• AI chatbot with structured memory using Make + HTTP + external LLM API
• Automated lead gen pipeline (Apify + Clay + CRM sync)
• Multi-route AI content workflows with structured Google Sheets logging
• API-driven Figma system with retry logic and error notifications

IMG_20260216_083533_907
IMG_20260216_083533_9071280×402 36.5 KB

IMG_20260216_083026_257
IMG_20260216_083026_2571280×635 95.4 KB

IMG_20260216_083017_040
IMG_20260216_083017_0401280×647 95.6 KB

I’m comfortable working directly with REST APIs, custom headers, polling endpoints, and data transformations.

Timeline & Pricing

Phase 1:
Timeline: 4–6 days including testing
Fixed Price: $450

Phase 2 (HeyGen):
Estimated: $250–$350 depending on rendering logic + polling structure
I can also provide clear documentation and a Loom-style walkthrough so you can manage and extend the system yourself.

You can reach me directly at
fopefoluwaakinola@gmail.com if easier.
Looking forward to discussing this further this is a great use case for Make.
Best,
Fopefoluwa

4

Hi @macdrazy ! I would love to help you with your flow. I have worked with Elevenlabs, HeyGen and other AI video generators. I would love to know more details bout this.

If you are interested we would love to help you, you can schedule a call in here: Automation Discovery Call | Felipe Saucedo | Cal.com discovery or check our website www.aspirity.com

5

Hello @macdrazy , welcome to make.com community, I have worked and have experience with Make.com and l will love to collaborate with you on this you can schedule a call Here and you can checkout my upwork profile Here, for my pastworks and certifications

6

Hi @macdrazy , I see you need a fully automated Make.com pipeline for your AI podcast workflow, from script parsing and ElevenLabs voice generation to Podsqueeze metadata and HeyGen video creation. I can build clean, scalable scenarios that watch Drive, segment scripts, generate assets, log everything in Sheets, and automate post-production with proper API handling and file organization. I’ve built similar multi-step Make automations involving AI generation, Google services, and webhook integrations. Phase 1 can be delivered in about 48 hours ($400), with Phase 2 scoped separately. Happy to share examples and a walkthrough. Schedule a call with me here to further discuss this.

7

Hi @macdrazy, welcome to the community.

I went through your workflow breakdown and this is definitely achievable with a properly structured Make setup. It’s a solid concept and I like how clearly you mapped the stages.

Before I give a fixed timeline and pricing for Phase 1 and Phase 2, I’d like to clarify a few things so I scope it correctly:

1. Will the script always follow a consistent speaker format (for example clear tags like Narrator, Marcus, Gigi), or should the parsing logic handle variations?

2. For ElevenLabs and HeyGen, do you already have API access confirmed for programmatic calls, or would we need to test any limitations?

3. For logging, do you prefer everything centralized in one master Google Sheet, or separated tracking per episode?

Once I get clarity on those, I can provide a clear timeline and fixed pricing for both phases.

You can review related automation samples on my website portfolio here.

You can respond directly to my email at folafoluwaolaneye@gmail.com, or we can discuss securely via my Fiverr workspace if you prefer structured project handling.

I’m also open to a walkthrough call to review your setup live. Kindly book a suitable time slot and we’ll go through everything together.

Looking forward to your response.

Best regards,

Folafoluwa Stephen

Flowedge Digitals

8

Hi @macdrazy,

This is a clean, well-scoped project. I work with AI APIs daily (ElevenLabs, OpenAI, Claude) and have built multi-step Make scenarios that orchestrate exactly this kind of pipeline — API calls, file management, conditional logic, and structured logging.

Here’s how I’d approach Phase 1:

Workflow 1 (Script to Audio): Google Drive watch trigger, parse the script by speaker tags (Narrator/Marcus/Gigi), iterate through segments, call ElevenLabs API with the correct voice ID per character, save audio files to organized Drive folders (EP##/Character/Line##.mp3), and log everything to your tracking Sheet with timestamps and file paths.

Workflow 2 (Audio to Show Notes): Drive watch on the final audio folder, HTTP call to Podsqueeze API, parse the returned metadata (titles, descriptions, timestamps, social captions), write to a Google Doc per episode, and update the master Sheet with links.

The key architectural decision is how to handle ElevenLabs rate limits and processing time — I’d use Make’s built-in sleep + polling or webhook callbacks depending on which the API supports, with error handling so a failed segment doesn’t break the whole episode.

Phase 1 estimate: $400 fixed, delivered in 5-7 days.

Phase 2 (HeyGen): I’d estimate $300-500 depending on HeyGen’s API capabilities for motion prompts and emotion mapping. Happy to scope this after Phase 1 is running.

I can share a quick Loom walkthrough of similar API-orchestration scenarios I’ve built. DM me here or email priyanshukumarmaurya2224@gmail.com.

Best,

Priyanshu Kumar

Founder, Evara AI