ENGINEERING

Re-Voice IVR Prompts on Phone-Tree Config Merge

When a phone-tree config change merges in GitHub, regenerates the ElevenLabs audio for any prompt whose script changed in the diff and opens a follow-up PR adding the new audio…

CategoryEngineering
Enginesim
Difficultyadvanced
Triggerevent
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerPhone-tree config PR merged in GitHubGitHubGitHub
  • ActionFetch diff and extract changed prompt scriptsGitHubGitHub
  • LogicDrop no-op edits; keep altered spoken lines
  • ActionSynthesize changed lines with ElevenLabsElevenLabsElevenLabs
  • ActionUpload new audio files to DropboxDropboxDropbox
  • OutputOpen follow-up PR wiring in new audio pathsGitHubGitHub

What it does

Treats the IVR phone tree as code. When a pull request that edits the phone-tree config (script strings and node names) merges to the main branch, the workflow reads the diff, synthesizes audio for each changed prompt, uploads the clips, and opens a follow-up pull request that wires the new audio paths into the config.

When to use it

Use this when your IVR definition lives in a Git repo and product renames arrive as config edits. It guarantees the spoken audio is regenerated and version-tracked alongside the text it came from.

How it works

  1. 1A merged pull request touching the phone-tree config file triggers the run.
  2. 2A GitHub action fetches the diff and extracts prompts whose script text changed.
  3. 3A logic step skips no-op edits like reordering and keeps only altered spoken lines.
  4. 4ElevenLabs synthesizes the changed lines to audio files.
  5. 5An action uploads the audio to Dropbox and records the resulting paths.
  6. 6The output step opens a follow-up pull request updating the config to point at the new audio files.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect GitHubRepos, issues, pull requests, actions.
  2. 2
    Connect ElevenLabsText-to-speech, voice cloning.
  3. 3
    Connect DropboxFiles and folders.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.