---
title: "Voice reply (dictate or smart)"
method: POST
path: "/tickets/{ticketId}/voice-reply"
tags: ["Ticket"]
---

# Voice reply (dictate or smart)

`POST /tickets/{ticketId}/voice-reply`

Process an operator's recorded audio for a ticket with one
multimodal model call. `dictate` returns a verbatim transcript; `smart`
treats the audio as spoken keywords and drafts a fluent reply using the
ticket + conversation as context (no knowledge-base retrieval). The client
uploads the audio via POST /uploads first and passes the resulting URL.

## Path parameters

- `ticketId` string, required

## Headers

- `project` string, required

## Request body

- object
  - `audioUrl` string, required — Public URL of the uploaded audio clip (from POST /uploads).
  - `mode` 'dictate' | 'smart', required — `dictate` returns the transcript; `smart` returns a drafted reply.

## Response `200`

Ok

- object
  - `reply` string
  - `transcript` string

---

[API](https://skmtc.net/gleap/apis/gleap-server.md) · [All operations](https://skmtc.net/gleap/apis/gleap-server/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/gleap/gleap-server/versions/2bfe054193b5/schema)