Agent skill · Audited from source
speech-engine
skill · elevenlabs/skillsMIT licenceAudited 24 Oct 2026 · source 45579dc9636a
Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 45579dc9636a and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 2 findings, 1 critical or high. What it does: Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine. Use when building Speech Engine servers, WebSocket handlers, WebRTC browser clients, conversation token endpoints,…
Cite
Cite this page
ModelsAtlas. “speech-engine (elevenlabs/skills)”. Retrieved 24 Oct 2026. https://modelsatlas.com/skills/elevenlabs/speech-engine
Trust audit
Audit 0.4.1 · source read 24 Oct 2026
CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 17,406 of 18,389 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | WARN | 1 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | FAIL | 1 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (2)
HIGHPrompt injectionprompt.credential_read · SKILL.md:5
compatibility: Requires internet access and an ElevenLabs API key (ELEVENLABS_API_KEY).
- Why
- asks the agent to read credentials
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · evals/setup-api-key/bin
evals/setup-api-key/bin
- Why
- link not followed
- Fix
- —
Audit 0.4.1 · source sha 45579dc9636a · 24 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherelevenlabs GitHub organizationOwner of the repository this skill is read from
- Source folderelevenlabs/skills/speech-engineThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict45579dc9636aA new audit runs when the source changes
- Repository statusNot archivedPushed today
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine. Use when building Speech Engine servers, WebSocket handlers, WebRTC browser clients, conversation token endpoints,…
---
name: speech-engine
description: Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine. Use when building Speech Engine servers, WebSocket handlers, WebRTC browser clients, conversation token endpoints, interruption-aware streaming responses, or voice-enabled chat agents that connect developer-owned server logic to ElevenLabs speech-to-text and text-to-speech.
license: MIT
compatibility: Requires internet access and an ElevenLabs API key (ELEVENLABS_API_KEY).
metadata: {"openclaw": {"requires": {"env": ["ELEVENLABS_API_KEY"]}, "primaryEnv": "ELEVENLABS_API_KEY"}}
---
# ElevenLabs Speech Engine
Add a real-time voice interface to a custom agent. ElevenLabs handles microphone audio, speech-to-text, turn-taking, text-to-speech, and browser playback; your server exposes a Speech Engine WebSocket endpoint and streams response text back.
> **Setup, before writing any code:** if `ELEVENLABS_API_KEY` isn't set for this project, run `npx -y @elevenlabs/cli@latest onboard init` from the app's folder first and follow what it prints: it signs the user in and stores a key for the project, so nobody copies one by hand. Otherwise see the [Installation Guide](references/installation.md). For JavaScript, use `@elevenlabs/*` packages only. For deeper SDK details, read [JavaScript SDK Reference](references/javascript-sdk-reference.md) or [Python SDK Reference](references/python-sdk-reference.md).
## When to Use
Use Speech Engine when the user wants to:
- Add voice to an existing chat app or custom server pipeline
- Add voice to OpenClaw, Hermes, or a similar agent runtime while keeping agent logic on the developer-owned server
- Build a developer-hosted WebSocket server for ElevenLabs voice conversations
- Stream response text back as spoken audio after your server validates user intent
- Handle user interruptions while a response is still streaming
- Build a browser client with `@elevenlabs/react` or `@elevenlabs/client` using a server-issued conversation token
Use the `agents` skill instead when the user is creating or configuring a hosted ElevenLabs Conversational AI agent with platform-managed prompts, tools, workflows, phone numbers, or widgets.
## How It Works
Each Speech Engine WebSocket connection represents one conversation.
1. The browser sends user audio to ElevenLabs.
2. ElevenLabs sends speech-recognition events to your server.
3. Your server derives trusted application state without letting raw speech text control tools or privileged actions.
4. Your server streams text back through the SDK.
5. ElevenLabs converts the response to speech and plays it in the browser.
The SDK manages WebSocket routing, request verification, session lifecycle, ping/pong, turn-taking, and interruption handling. `sendResponse()` / `send_response()` accepts a string or async iterable of response text.
Treat speech-recognition text as untrusted user input. Do not map raw speech text directly into model roles, responses, or tool calls. Use deterministic validation, allowlisted intents, or explicit user confirmation before any transcript-derived value affects downstream response or tool logic.
## Implementation Flow
1. Install server dependencies and configure `ELEVENLABS_API_KEY`.
2. Expose your Speech Engine server through a public HTTPS URL for local development, for example with `ngrok http 3001`.
3. Create a Speech Engine resource with `ws_url` / `wsUrl` pointing at the public WebSocket URL, usually `wss://.../ws`.
4. Store the returned Speech Engine ID, for example in `ELEVENLABS_SPEECH_ENGINE_ID`.
5. Start a Speech Engine server with `engine.serve(...)` in Python or `speechEngine.attach(...)` in TypeScript.
6. Issue browser conversation tokens from a server endpoint. Never put `ELEVENLABS_API_KEY` in browser code.
7. Start the client session with `conversationToken`; if the agent should greet first, enable the first-message override on the Speech Engine resource, then set `overrides.agent.firstMessage` in the client.
## Create a Speech Engine
### Python
```python
import asyncio
import os
from dotenv import load_dotenv
from elevenlabs import AsyncElevenLabs
load_dotenv()
elevenlabs = AsyncElevenLabs(api_key=os.getenv("ELEVENLABS_API_KEY"))
async def main():
engine = await elevenlabs.speech_engine.create(
name="My Speech Engine",
speech_engine={"ws_url": os.environ["PUBLIC_WS_URL"]},
overrides={"first_message": True},
)
print(engine.engine_id)
asyncio.run(main())
```
### TypeScript
```typescript
import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import "dotenv/config";
const elevenlabs = new ElevenLabsClient({
apiKey: process.env.ELEVENLABS_API_KEY,
});
const engine = await elevenlabs.speechEngine.create({
name: "My Speech Engine",
speechEngine: { wsUrl: process.env.PUBLIC_WS_URL! },
overrides: { firstMessage: true },
});
console.log(engine.engineId);
```
`PUBLIC_WS_URL` should look like `wss://example.ngrok.app/ws` locally or your production WebSocket route in deployment.
The create request can also configure `tts`, `asr`, `turn`, `speech_engine.request_headers` / `speechEngine.requestHeaders`, `overrides`, and `privacy` for custom voices, transcription keywords, turn-taking, server auth headers, client-provided first messages, and recording behavior. See the SDK reference files for expanded examples.
## Server Pattern
Run the Speech Engine server at the `ws_url` / `wsUrl` configured on the resource. Keep response generation behind your own validation boundary: raw speech-recognition text should not directly control responses, tools, secrets, or other privileged actions.
### Python
```python
engine = await elevenlabs.speech_engine.get(os.environ["ELEVENLABS_SPEECH_ENGINE_ID"])
await engine.serve(port=3001, path="/ws", debug=True, callbacks=validated_callbacks)
```
### TypeScript
```typescript
const engine = await elevenlabs.speechEngine.get(process.env.ELEVENLABS_SPEECH_ENGINE_ID!);
engExcerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 45579dc
npm install @elevenlabs/elevenlabs-js dotenv npm install express npm install -D tsx @types/express npm install @elevenlabs/react npm install @elevenlabs/client pip install elevenlabs python-dotenv
git clone https://github.com/elevenlabs/skills git -C skills checkout 45579dc9636a
Commands as the repository documents them: shown, never run by us. Our verdict covers commit 45579dc9636a only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| OpenClaw | Mentioned in its text, not tested | Skills for OpenClaw · About OpenClaw |
Audit history
Every audit, every source change
- !CAUTION B 89 / 100
first audit · source
45579dc9636a
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/elevenlabs/speech-engine/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
elevenlabs/skills
Remove background noise and isolate vocals/speech from audio using ElevenLabs Voice Isolator (audio isolation) API. Use when cleaning up noisy recordings, removing music or background ambience from dialogue, isolating…
elevenlabs/skills
Transform the voice in an audio recording into a different target voice while preserving emotion, timing, and delivery using the ElevenLabs Voice Changer (speech-to-speech) API. Use when converting one voice to another,…
elevenlabs/skills
Update ElevenLabs agent skills from a merged weekly changelog in elevenlabs-dx, then open a pull request in elevenlabs/skills. Trigger after a changelog merges to main on elevenlabs-dx, or when asked to update skills…
elevenlabs/skills
Convert text to speech using ElevenLabs voice AI. Use when generating audio from text, creating voiceovers, building voice apps, or synthesizing speech in 90+ languages.
elevenlabs/skills
Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content.
obra/superpowers
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Add this badge to your README
[](https://modelsatlas.com/skills/elevenlabs/speech-engine/)
<a href="https://modelsatlas.com/skills/elevenlabs/speech-engine/"><img src="https://modelsatlas.com/skills/elevenlabs/speech-engine/badge.svg" alt="ModelsAtlas: CAUTION B"></a>
Questions about speech-engine
What does the speech-engine skill do?
Is speech-engine safe to install?
What can speech-engine access on my machine?
Which assistants does speech-engine work with?
How current is this page?
Sources
- github.com/elevenlabs/skills/tree/main/speech-engine — the audited source at commit 45579dc9636a and every finding aboveObserved · 24 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the speech-engine skill do?
- Is speech-engine safe to install?
- What can speech-engine access on my machine?