Tool #13 · On the bench · On the bench

Outbound & Inbound Voice AgentsRetell AI

Built in a draft branch for the RiseSync morning voice-coach call; demoed on our own account, not live for end users yet.

Last reviewed: 2026-10-22 · Status: On the bench

Full stack receipt#13 · On the bench · reviewed 2026-10-22
#13Outbound & Inbound Voice Agents

Retell AI

On the bench
1. What we use it for: We are testing Retell AI (orchestrating GPT-4.1, ElevenLabs TTS, and Twilio telephony) to place scheduled morning voice-coach calls for RiseSync and log answers via webhook.
2. Client use case · RiseSyncState: built-not-live
Problem

RiseSync’s Milestone 2 scope adds a scheduled morning phone call that walks a user through their daily coaching check-in and records their spoken answers.

What the tool did

Wired Retell AI (`src/retell.ts` on branch `feat/m2-voice-coach`, commit `c25644e`) into our `voice-coach-engine` (which enforces safety rules, 49 test scenarios, and call scheduling) and ran a live prototype call on our own account on 2026-10-17.

Result

Built-not-live in a draft branch; waiting on Milestone 2 launch and final production voice/model selection before going live to RiseSync users.

3. What it costs us or the client

Pay-as-you-go per-minute voice API (~$0.07–$0.15/minute combined Retell + GPT-4.1 + ElevenLabs TTS + Twilio telephony in our 2026-10-17 call record) (as of 2026-10-22).

4. Setup notes (how it is wired in)

Triggered by our `voice-coach-engine` scheduler, which places the outbound call through Retell and receives the post-call webhook to write structured answers to the user’s record.

5. What broke & how it was handled

Production LLM, voice selection, and the client’s dedicated Retell account are not finalized yet—so per our honesty rules, we list Retell AI as On the bench rather than live in client work.

6. What we compared it against & why we picked it

Compared against OpenAI GPT-Live + LiveKit (running live in our own `moHelp` product and internal `call-bizv2` caller) and Vapi (used in 27 internal phone-screener sessions).

7. Last reviewed: 2026-10-228. Video / tutorial: On the bench segment planned once RiseSync Milestone 2 voice coach goes live
All stack tools
How an engagement runsthree steps, in order

Three separate steps. Stop after any of them.

Step 1 is a free 15-minute fit call. Step 2 is the AI Staff Assessment, $500, a written assessment you keep. Step 3 is your first hire at a published price, or you take the assessment and stop.

Step 1

Fit call

$0 · 15 min
  • tell me which job eats your week: the phone, the inbox, marketing or support
  • I tell you whether an AI hire fits, and whether I am the right person for it
  • you leave with the first hire I would start with
  • a slide deck

video call · same week

book it
Step 2

AI Staff Assessment

$500
  • a 60-minute video call about how your business runs
  • my written assessment the same day: whether an AI hire would pay for itself, the job I would hand off first, what to settle first, and the fixed price for that first hire
  • not taken off the build, and no separate quoting call: the assessment names the package at its published price
  • proposals written before anyone learned your business

paid when you book · not taken off the build

start here
Step 3

Your first hire

fixed price
  • Front Desk Hire or Brain + First Hire, at the published price
  • built in 2 to 6 weeks, then 30 days of tuning
  • or take the assessment and stop there
  • bench developers you never met

priced in the assessment

see the prices

Want Retell AI wired into your business?

Bring the workflow or codebase to a free 15-minute fit call. We will tell you how we wire Retell AI in production, what breaks first, and whether a $500 AI Staff Assessment fits your scope.