Sales enablement
Voice roleplay trainer
Reps practise live sales calls against an AI counterpart: speech in, transcription, a scenario-conditioned model turn, synthesised speech back — a full conversational loop that has to feel like a phone call, not a chatbot.
Pipeline
- capture audio
- transcribe
- scenario context
- model turn
- synthesise voice
- stream back
01The brief
What made this hard.
The problem
Latency is the whole product. A roleplay that pauses between turns stops being practice and starts being a form.
The approach
The audio round trip is split into independently tunable stages — transcription, model turn, synthesis — so each can be optimised or swapped without touching the others. Scenario state is carried across turns so the AI counterpart stays in character for the length of a real call.
02In production
What it actually does, day to day.
- Full duplex voice loop, tuned stage by stage
- Scenario state persists across a multi-turn call
- Provider-swappable transcription and synthesis layers
Stack
03More systems
Others we have shipped.
04Start here
Tell us what you are building. We will tell you what it takes.
Four short steps, then a real conversation with the engineer who would build it. No sales call, no discovery deck.
Rather just talk?
Grab 45 minutes. You will be on with an engineer, not a salesperson.
- No NDA needed to have the first conversation
- You keep the architecture note either way
- We will tell you if we are the wrong fit