Gong ACTION
Get Call Transcripts
Retrieve the full spoken transcript of one or more calls. Returns an array of { callId, speakers, transcript } objects, where each transcript entry carries the speaker, the topic Gong assigned to that stretch of the call, and the sentences with their hh:mm:ss offset from the start of the call.
Pass Call IDs to transcribe specific calls (use List Calls or Search Calls to find them), or a date range to transcribe everything recorded in that window. Speaker IDs are resolved to participant names automatically, so you can tell the rep and the customer apart.
To find where a word or phrase was said without pulling whole transcripts back, use Search Call Transcripts instead. For summaries, topics, and next steps, use Search Calls.
Transcripts exist only for calls Gong has processed; a recently uploaded call may return nothing. Results are paginated internally, so one run returns up to Limit transcripts. See the documentation
- Action
- Read only
- OAuth
- SDK
- MCP
IMPLEMENTATION
Call this tool
Connect a user's Gong account once, then configure and run Get Call Transcripts from your backend or agent.
import { PipedreamClient } from "@pipedream/sdk"
const pd = new PipedreamClient({
projectId: process.env.PIPEDREAM_PROJECT_ID!,
clientId: process.env.PIPEDREAM_CLIENT_ID!,
clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
projectEnvironment: "production",
})
const result = await pd.actions.run({
id: "gong-retrieve-transcripts-of-calls",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
gong: { authProvisionId: "apn_xxxxxxx" },
fromDateTime: "From Date Time",
toDateTime: "To Date Time",
},
})
console.log(result)curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
-H "Content-Type: application/json" \
-H "X-PD-Environment: production" \
-H "Authorization: Bearer {access_token}" \
-d '{
"external_user_id": "{external_user_id}",
"id": "gong-retrieve-transcripts-of-calls",
"configured_props": {
"gong": { "authProvisionId": "apn_xxxxxxx" },
"fromDateTime": "From Date Time",
"toDateTime": "To Date Time"
}
}'// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
new URL("https://remote.mcp.pipedream.net/v3"),
{
requestInit: {
headers: {
Authorization: `Bearer ${accessToken}`,
"x-pd-project-id": "{project_id}",
"x-pd-environment": "production",
"x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
"x-pd-app-slug": "gong",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
name: "gong-retrieve-transcripts-of-calls",
arguments: {
fromDateTime: "From Date Time",
toDateTime: "To Date Time",
},
})SCHEMA
Inputs
Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.
| Property | Type | Description |
|---|---|---|
fromDateTime From Date Time | string | Only transcribe calls that started on or after this date and time, in ISO-8601 format (e.g. 2026-01-01T00:00:00Z). Optional |
toDateTime To Date Time | string | Only transcribe calls that started before this date and time, in ISO-8601 format (e.g. 2026-04-01T00:00:00Z). The bound is exclusive. Optional |
workspaceId Workspace ID | string | Only transcribe calls belonging to this workspace. Cannot be combined with Call IDs. Use the List Workspace ID Options action to discover workspace IDs. Optional Dynamic |
callIds Call IDs | string[] | Transcribe only these calls. Cannot be combined with Workspace ID. Use List Calls to discover call IDs. Optional Dynamic |
resolveSpeakerNames Resolve Speaker Names | boolean | Whether to look up each speaker's name, email, and Internal or External affiliation. Costs one extra request per batch of calls. Turn off to return raw speaker IDs only. Optional |
returnSimplifiedTranscript Return Simplified Transcript | boolean | Whether to return one readable text block per call instead of the structured sentence arrays. Easier to read, but drops the per-sentence timing. Optional |
limit Limit | integer | Maximum number of call transcripts to return. Min 1, max 1000. Optional |
REFERENCE
Tool details
Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.
- Registry key
- gong-retrieve-transcripts-of-calls
- Version
- 1.0.0
- App
- Gong
- Authentication
- OAuth
- Read-only
- Yes
- Destructive
- No
- Open world
- Yes
- Source
- View on GitHub ↗