Skip to main content
This endpoint returns the full transcript of a call with AI-resolved speaker labels applied. Shilo identifies each segment of the conversation and maps it to either the agent or the contact by name, giving you a clean, readable record of who said what. Because speaker resolution depends on the AI analysis pipeline completing successfully, the transcript is not available until progress on the analysis endpoint reaches 100. Requesting the transcript before that point returns a 409 Conflict response.
This endpoint is not available for organizations connected to Follow Up Boss. Requests from Follow Up Boss-integrated accounts will receive a 403 Forbidden response regardless of analysis status.

Endpoint

Path Parameter

string
required
Identifies the call whose transcript you want to retrieve. The same three formats accepted by GET /calls/{identifier} are supported here:

Response

A successful request returns HTTP 200 with a transcript object containing speaker-labeled segments. The exact structure of the transcript JSON varies by AI model configuration, but each segment includes the speaker’s resolved name and the text they spoke.
Before requesting the transcript, poll GET /calls/{identifier}/analysis until the progress field equals 100. Requesting the transcript while analysis is still running will return a 409 Conflict error. Speaker resolution must be fully complete before transcripts are served.

Example Response

Example Request

Error Responses

400 Bad Request — The identifier format is invalid or cannot be parsed.
403 Forbidden — Your organization’s CRM integration does not support transcript access. This error is returned for all Follow Up Boss-connected accounts.
404 Not Found — No call matching the provided identifier exists in your organization.
409 Conflict — The transcript is not yet available because AI analysis and speaker resolution have not completed. Poll GET /calls/{identifier}/analysis until progress equals 100, then retry this request.