# Search Call Transcripts — Gong

> Find where a word or phrase was said across call transcripts. Returns one entry per matching sentence with the call's ID, title and URL, the speaker's name and affiliation, the hh:mm:ss offset into the call, and the sentence itself, so you…

- Key: `gong-search-call-transcripts`
- Type: Action (Read-only)
- Version: 0.0.1
- App: Gong (`gong`) — https://pipedream.com/apps/gong.md
- This page (HTML): https://pipedream.com/apps/gong/actions/search-call-transcripts
- Hints: read-only · open-world
- Source: https://github.com/PipedreamHQ/pipedream/blob/master/components/gong/actions/search-call-transcripts/search-call-transcripts.mjs

## Description

Find where a word or phrase was said across call transcripts. Returns one entry per matching sentence with the call's ID, title and URL, the speaker's name and affiliation, the `hh:mm:ss` offset into the call, and the sentence itself, so you can quote what was said and link straight to that moment. Use this to answer questions like "which calls mentioned pricing" or "did anyone bring up the competitor". Narrow the search with a date range, a workspace, or specific **Call IDs**; the search itself runs over the transcript text. Prefer this over **Get Call Transcripts** whenever you are looking for a keyword rather than reading a call end to end - it scans the same transcripts but returns only the matching lines. Note that it fetches transcripts for every call in the window in order to search them, so a narrow date range is much cheaper than a wide one. [See the documentation](https://gong.app.gong.io/settings/api/documentation#post-/v2/calls/transcript)

## Props

| Prop | Type | Required | Description |
|---|---|---|---|
| `keyword` | `string` | Yes | The word or phrase to search for. Matching is case-insensitive and matches anywhere in a sentence (e.g. pricing also matches Pricing model). |
| `wholeWord` | `boolean` | No | Whether to require the keyword to appear as a whole word, so AI does not match said. Leave off to match substrings. |
| `fromDateTime` | `string` | No | Only search calls that started on or after this date and time, in ISO-8601 format (e.g. 2026-01-01T00:00:00Z). |
| `toDateTime` | `string` | No | Only search calls that started before this date and time, in ISO-8601 format (e.g. 2026-04-01T00:00:00Z). The bound is exclusive. |
| `workspaceId` | `string` | No | Only search calls belonging to this workspace. Cannot be combined with Call IDs. Use the List Workspace ID Options action to discover workspace IDs. Options are loaded from the connected account. |
| `callIds` | `string[]` | No | Only search these calls. Cannot be combined with Workspace ID. Use List Calls to discover call IDs. Options are loaded from the connected account. |
| `maxCalls` | `integer` | No | Maximum number of call transcripts to scan. Min 1, max 1000. Raise this to widen the search. |
| `limit` | `integer` | No | Maximum number of matching sentences to return. Min 1, max 1000. |

## Run it

**MCP**

```ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js"
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"
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 accessToken = await pd.rawAccessToken

const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": process.env.PIPEDREAM_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-search-call-transcripts",
  arguments: {
    keyword: "Keyword",
    wholeWord: true,
  },
})
```

**TypeScript**

```ts
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-search-call-transcripts",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    gong: { authProvisionId: "apn_xxxxxxx" },
    keyword: "Keyword",
    wholeWord: true,
  },
})

console.log(result)
```

**cURL**

```bash
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-search-call-transcripts",
    "configured_props": {
      "gong": { "authProvisionId": "apn_xxxxxxx" },
      "keyword": "Keyword",
      "wholeWord": true
    }
  }'
```

---

- App: https://pipedream.com/apps/gong.md · All apps: https://pipedream.com/apps
