# Submit Audio URL — Symbl.ai

> Submit an Audio file by providing the URL for processing. See the doc here.

- Key: `symbl_ai-post-audio-url`
- Type: Action (Write)
- Version: 0.0.6
- App: Symbl.ai (`symbl_ai`) — https://pipedream.com/apps/symbl-ai.md
- This page (HTML): https://pipedream.com/apps/symbl-ai/actions/post-audio-url
- Hints: open-world
- Source: https://github.com/PipedreamHQ/pipedream/blob/master/components/symbl_ai/actions/post-audio-url/post-audio-url.mjs

## Description

Submit an Audio file by providing the URL for processing. See the doc [here](https://docs.symbl.ai/docs/async-api/overview/audio/post-audio-url).

## Props

| Prop | Type | Required | Description |
|---|---|---|---|
| `audioUrl` | `string` | Yes | The URL of the audio file to be processed. |
| `meetingName` | `string` | No | The meeting name. The default name is set to the conversationId. |
| `customVocabulary` | `string[]` | No | List of words and phrases that provide hints to the speech recognition task. |
| `confidenceThreshold` | `string` | No | Minimum confidence score that you can set for an API to consider it as a valid insight (action items, follow-ups, topics, and questions). It should be in the range <=0.5 to <=1.0 (i.e., greater than or equal to 0.5 and less than or equal to 1.0.). The default value is 0.5. |
| `detectPhrases` | `boolean` | No | It shows Actionable Phrases in each sentence of conversation. These sentences can be found using the Conversation's Messages API. Accepts true or false values. |
| `webhookUrl` | `string` | No | Webhook URL on which job updates to be sent. |
| `detectEntities` | `boolean` | No | It returns any entities detected in the conversation. See Entities API for reference. Default value is false. |
| `languageCode` | `string` | No | Language used in the conversation. See supported languages for reference. Default language is English (en-US). |
| `mode` | `string` | No | Set this parameter to phone when the audio is generated from a phone call (8khz sampling rate). The default mode works for audio generated from a video or audio meeting (16khz or higher sampling rate). |
| `enableSeparateRecognitionPerChannel` | `boolean` | No | Enables Speaker Separated Channel audio processing. Accepts true or false values. |
| `enableAllTrackers` | `boolean` | No | Set this parameter to true to enable detection of all the Trackers configured for your account. Default value is false. |
| `enableSpeakerDiarization` | `boolean` | No | Set this parameter to true to enable Speaker Separation. Default value is false. See Speaker Separation for reference. |
| `diarizationSpeakerCount` | `string` | No | The number of unique speakers in this conversation. See Speaker Separation for reference. |
| `trackers` | `string` | No | Provide a JSON array of the information to be tracked containing the name and the vocabulary information. The tracker object is represented by the following structure: [{"name": "Promotion Mention","vocabulary": ["We have a special promotion going on if you book this before","I can offer you a discount of 10 or 20 percent you being a new customer for us","We have a sale right now on"]}]. See doc here. |
| `channelMetadata` | `string` | No | Provide a JSON array of participants with their channel and speaker information. Each participant object is represented by the following structure: [{"channel": 1,"speaker": {"name": "Joe Doe","email": "joe@doe.com"}},{"channel": 2,"speaker": {"name": "Mary Jones","email": "mary@email.com"}}]. See doc here |
| `enableSummary` | `boolean` | No | Generate the Conversation summary automatically. Accepts true or false values. |

## 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": "symbl_ai",
      },
    },
  },
)

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: "symbl_ai-post-audio-url",
  arguments: {
    audioUrl: "Audio URL",
    meetingName: "Meeting Name",
  },
})
```

**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: "symbl_ai-post-audio-url",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    symbl_ai: { authProvisionId: "apn_xxxxxxx" },
    audioUrl: "Audio URL",
    meetingName: "Meeting Name",
  },
})

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": "symbl_ai-post-audio-url",
    "configured_props": {
      "symbl_ai": { "authProvisionId": "apn_xxxxxxx" },
      "audioUrl": "Audio URL",
      "meetingName": "Meeting Name"
    }
  }'
```

---

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