SOCIAL MEDIA
Generate A/B audiogram variants in multiple ElevenLabs voices
From one quote, narrates the same line in several ElevenLabs voices, builds a captioned audiogram for each.
How it runs
The automated pipeline, trigger to output.
- TriggerWebhook receives quote text and a list of voice IDsHTTP webhook
- LogicLoop over each voice ID in the list
- ActionElevenLabs narrates the quote in the current voiceElevenLabs
- ActionRender shared card and composite a captioned audiogram variantImage generation
- OutputUpload all variants to a dated Google Drive folderGoogle Drive
What it does
Takes a single quote and a list of ElevenLabs voice IDs, then produces one captioned audiogram per voice. All variants land in a dated Google Drive folder so you can compare voices side by side and choose a winner before anything goes public.
When to use it
When you're tuning brand voice and want to A/B test how a quote lands across different ElevenLabs narrators. This is a generation-and-staging workflow; posting stays a separate human decision.
How it works
1. A webhook receives the quote text and an array of voice IDs. 2. A logic step iterates over each voice in the list. 3. ElevenLabs narrates the quote once per voice into separate MP3s. 4. An image step renders a shared branded card and a logic step composites a captioned audiogram for each variant. 5. Every variant is uploaded to a dated Google Drive folder named for the quote. The folder becomes your side-by-side comparison set for picking the strongest voice.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect ElevenLabsText-to-speech, voice cloning.
- 3Connect Image generationManaged Nano Banana image renders, metered per image.
- 4Connect Google DriveDocs, sheets, slides, files.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Social Media workflows
Discord event capacity gate with automatic waitlist promotion
Enforces a seat cap on RSVPs: once an event is full, new sign-ups join a waitlist, and when someone drops out the next person is promoted, notified in Discord.
Tiered Discord event reminder fan-out (24h / 1h / live)
On a schedule, scans upcoming Discord-tracked events and DMs each confirmed attendee staged reminders at 24 hours, 1 hour, and event start.
A/B carousel cover variants from one brief
Takes a single approved brief and uses an LLM to write three distinct cover-slide headlines, renders a carousel cover for each, and logs the variants to Airtable for an A/B test.
Localized carousel variants per target market
From one approved master brief, translates the copy into each target locale, renders a localized carousel per market, and publishes each to its region's platform account.
Carousel render and auto-publish on Slack approval
Renders carousel variants from a brief, posts a preview to Slack for a one-click approve, and on approval publishes the chosen variant to the connected social platforms.
Discord /rsvp slash command with Outlook calendar invite
Lets members RSVP to an event via a /rsvp slash command, captures their status (yes/maybe/no), and sends a matching Outlook calendar invitation or cancellation to their email.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.