# dubbing_project_create

Create Dubbing Project. Spends ElevenLabs credits.

Agent View of the PolicyLayer registry record for `dubbing_project_create`. HTML page: https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/dubbing-project-create

## Facts

- Tool: `dubbing_project_create`
- Server: Elevenlabs (`@aiwerk/mcp-server-elevenlabs`) — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs.md
- Install: `npx -y @aiwerk/mcp-server-elevenlabs`
- Homepage: https://www.npmjs.com/package/@aiwerk/mcp-server-elevenlabs
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 12
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `keyterms` | array | no | Key terms to bias transcription and translation toward (for example, product or brand names). At most 1,000 terms; each term at most 50 characters and 5 words; |
| `model_id` | string | null | no | Dubbing model (`dubbing_v1` or `dubbing_v2`) every language target of this project is dubbed with. Defaults to `dubbing_v2`. Fixed at create time — the source i |
| `file_path` | string | no | The source media file to dub: an audio or video file of at most 3 GiB. Provide this or `source_url`, not both. Local path. |
| `reference` | string | null | no | Optional free-form string (at most 500 characters) to identify the project on your end. Stored and echoed back verbatim; it does not affect the dub. |
| `source_url` | string | null | no | Public HTTP(S) URL the source media is fetched from server-side, subject to the same size and format limits as an upload. Provide this or `file`, not both. |
| `file_base64` | string | no | Base64 contents for "file". Use this when the server cannot read your local disk. |
| `webhook_ids` | array | no | IDs of workspace webhooks to notify as this project progresses — the alternative to polling, and what we recommend. Each receives a `dubbing_project_ready` or ` |
| `file_filename` | string | no | Filename to send for "file". Some endpoints infer the audio format from it. |
| `source_language` | string | null | no | BCP-47 language tag of the source media; must be a language the transcription model supports. Any region or script subtag is ignored, since transcription is per |
| `target_language` | string | null | no | Optional shortcut: also create a language target in this BCP-47 language, queued to start once the project is ready — equivalent to creating the project and the |
| `transcript_path` | string | no | Enterprise only. Optional JSON transcript to use instead of transcribing the source: a `{"segments": [...]}` document, at most 20,000 segments and 4 MiB. See [B |
| `transcript_base64` | string | no | Base64 contents for "transcript". Use this when the server cannot read your local disk. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "dubbing_project_create",
    "arguments": {}
  }
}
```

## Why dubbing_project_create is rated Medium

An AI agent can call dubbing_project_create faster than any human can review: one bad instruction and it creates or modifies resources in Elevenlabs by the hundred, each call as confident as the last.

Risk signals: Accepts file system path (file_path) · High parameter count (13 properties)

## Use case

AI agents use dubbing_project_create to create or update resources in Elevenlabs, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Elevenlabs environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Elevenlabs:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "dubbing_project_create": {
      "limits": [
        {
          "counter": "dubbing_project_create_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Elevenlabs (389)

- `cancel_batch_call` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/cancel-batch-call.md
- `cancel_crawl_job_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/cancel-crawl-job-route.md
- `cancel_file_upload_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/cancel-file-upload-route.md
- `delete_agent_conversation_ticket_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-agent-conversation-ticket-route.md
- `delete_agent_draft_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-agent-draft-route.md
- `delete_agent_hold_audio_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-agent-hold-audio-route.md
- `delete_agent_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-agent-route.md
- `delete_agent_test_folder_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-agent-test-folder-route.md
- `delete_asset_endpoint` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-asset-endpoint.md
- `delete_audio_isolation_history_item` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-audio-isolation-history-item.md
- `delete_auth_connection` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-auth-connection.md
- `delete_batch_call` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-batch-call.md
- `delete_chapter_endpoint` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-chapter-endpoint.md
- `delete_chat_response_test_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-chat-response-test-route.md
- `delete_conversation_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-conversation-route.md
- `delete_conversation_tag_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-conversation-tag-route.md
- `delete_dubbing` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-dubbing.md
- `delete_finetune` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-finetune.md
- `delete_invite` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-invite.md
- `delete_knowledge_base_document` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-knowledge-base-document.md
- `delete_mcp_server_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-mcp-server-route.md
- `delete_phone_number_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-phone-number-route.md
- `delete_procedure_draft_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-procedure-draft-route.md
- `delete_project` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-project.md
- `delete_pvc_voice_sample` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-pvc-voice-sample.md
- `delete_rag_index` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-rag-index.md
- `delete_sample` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-sample.md
- `delete_secret_route` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-secret-route.md
- `delete_segment` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-segment.md
- `delete_service_account_api_key` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs/delete-service-account-api-key.md
- …and 359 more: https://policylayer.com/tools/aiwerk-mcp-server-elevenlabs.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=aiwerk-mcp-server-elevenlabs · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/aiwerk-mcp-server-elevenlabs