Grain ACTION
Get Transcript
Fetches the full transcript of a Grain recording. The
json format returns structured segments with speaker, participant ID, start/end times in milliseconds, and text; txt, vtt, and srt return plain text or subtitle formats. Use List Recordings to find recording IDs; use Get Recording for the recording's metadata instead of its transcript. Example: recordingId: "pppp6666-qq77-rr88-ss99-tttt00000000" with format: "txt" returns plain text like "Speaker 1: Thanks for joining today...". See the documentation- Action
- Read only
- OAuth
- SDK
- MCP
IMPLEMENTATION
Call this tool
Connect a user's Grain account once, then configure and run Get Transcript 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: "grain-get-transcript",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
grain: { authProvisionId: "apn_xxxxxxx" },
recordingId: "Recording ID",
format: "Format",
},
})
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": "grain-get-transcript",
"configured_props": {
"grain": { "authProvisionId": "apn_xxxxxxx" },
"recordingId": "Recording ID",
"format": "Format"
}
}'// 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": "grain",
},
},
},
)
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: "grain-get-transcript",
arguments: {
recordingId: "Recording ID",
format: "Format",
},
})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 |
|---|---|---|
recordingId Recording ID | string | The ID of the recording to fetch. Use List Recordings to find recording IDs. Required |
format Format | string | Format for the transcript Required |
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
- grain-get-transcript
- Version
- 0.0.3
- App
- Grain
- Authentication
- OAuth
- Read-only
- Yes
- Destructive
- No
- Open world
- Yes
- Source
- View on GitHub ↗