# text_to_speech_v3

Converts text to speech with v3 model and tags. Returns: audio file path. Use when: single speaker needs emotions, pauses, or sound effects.

Agent View of the PolicyLayer registry record for `text_to_speech_v3`. HTML page: https://policylayer.com/tools/199-mcp-mcp-elevenlabs/text-to-speech-v3

## Facts

- Tool: `text_to_speech_v3`
- Server: ElevenLabs MCP Enhanced (`199-mcp/mcp-elevenlabs`) — https://policylayer.com/tools/199-mcp-mcp-elevenlabs.md
- Homepage: https://github.com/199-mcp/mcp-elevenlabs
- Risk category: Write (Medium risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "text_to_speech_v3",
    "arguments": {}
  }
}
```

## Why text_to_speech_v3 is rated Medium

This tool generates and writes an audio file to disk. It creates new data (an audio file) as a side effect, making it a Write operation. It does not delete data, execute arbitrary code, or involve financial transactions. Severity is medium because it consumes API credits and writes files to the filesystem, but the blast radius of misuse is limited.

From the tool's own definition: "Converts text to speech with v3 model and tags. Returns: audio file path."

## Use case

AI agents use text_to_speech_v3 to create or update resources in ElevenLabs MCP Enhanced, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ElevenLabs MCP Enhanced environment.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "text_to_speech_v3": {
      "limits": [
        {
          "counter": "text_to_speech_v3_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on ElevenLabs MCP Enhanced (28)

- `isolate_audio` — Execute — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/isolate-audio.md
- `make_outbound_call` — Execute — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/make-outbound-call.md
- `play_audio` — Execute — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/play-audio.md
- `speech_to_speech` — Execute — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/speech-to-speech.md
- `text_to_dialogue` — Execute — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/text-to-dialogue.md
- `text_to_sound_effects` — Execute — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/text-to-sound-effects.md
- `check_subscription` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/check-subscription.md
- `fetch_v3_tags` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/fetch-v3-tags.md
- `get_agent` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/get-agent.md
- `get_conversation` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/get-conversation.md
- `get_conversation_transcript` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/get-conversation-transcript.md
- `get_v3_audio_tags_guide` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/get-v3-audio-tags-guide.md
- `get_voice` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/get-voice.md
- `get_voice_id_by_name` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/get-voice-id-by-name.md
- `list_agents` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/list-agents.md
- `list_conversations` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/list-conversations.md
- `list_models` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/list-models.md
- `list_phone_numbers` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/list-phone-numbers.md
- `search_voice_library` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/search-voice-library.md
- `search_voices` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/search-voices.md
- `speech_to_text` — Read — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/speech-to-text.md
- `add_knowledge_base_to_agent` — Write — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/add-knowledge-base-to-agent.md
- `create_agent` — Write — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/create-agent.md
- `create_voice_from_preview` — Write — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/create-voice-from-preview.md
- `enhance_dialogue` — Write — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/enhance-dialogue.md
- `text_to_speech` — Write — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/text-to-speech.md
- `text_to_voice` — Write — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/text-to-voice.md
- `voice_clone` — Write — https://policylayer.com/tools/199-mcp-mcp-elevenlabs/voice-clone.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=199-mcp-mcp-elevenlabs · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/199-mcp-mcp-elevenlabs