What is elevenlabs-speech-engine?

A server-side SDK for adding real-time voice to an existing agent or workflow. ElevenLabs handles microphone audio, speech-to-text, turn detection, and text-to-speech, while your server handles the agent's reply.

Use it to add voice conversations to a hosted chat agent, LangGraph workflow, containerized language-model service, or similar server.

It avoids building the full audio pipeline yourself and lets an existing text-based agent accept spoken input and return spoken responses.

elevenlabs-speech-engine — Skill for Claude Code and Codex by jakenuts

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add jakenuts/agent-skills --skill elevenlabs-speech-engine

Clone the repo

git clone --depth 1 https://github.com/jakenuts/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jakenuts/agent-skills/elevenlabs-speech-engine/github.svg)](https://agentmods.dev/skills/jakenuts/agent-skills/elevenlabs-speech-engine)

Your own site

<a href="https://agentmods.dev/skills/jakenuts/agent-skills/elevenlabs-speech-engine"><img src="https://agentmods.dev/badge/skills/jakenuts/agent-skills/elevenlabs-speech-engine/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jakenuts/agent-skills/elevenlabs-speech-engine"><img src="https://agentmods.dev/badge/skills/jakenuts/agent-skills/elevenlabs-speech-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 226 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,649 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00226	$0.03649
Opus 5.5	$0.00090	$0.01460
Sonnet 5.5	$0.00045	$0.00730
Haiku 4.5	$0.00023	$0.00365

Measured 2mo ago against content hash 35c4046779ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

elevenlabs-speech-engine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/elevenlabs-speech-engine/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ElevenLabs Speech Engine

Speech Engine is the server-side product that lets you keep your existing agent (any LLM/workflow that produces text) and bolt a real-time voice interface in front of it. ElevenLabs runs everything between the microphone and the LLM call; you only handle "transcript in, reply text out."

[Browser / Mobile]            [ElevenLabs Cloud]               [Your Server]
       │                              │                              │
       │ 1. signed URL request ─────▶ │                              │
       │ ◀──── signed URL (15 min) ─  │                              │
       │ 2. WebRTC audio ──────────▶  │                              │
       │                              │ 3. STT + VAD + turn detect   │
       │                              │ 4. WS open ─────────────────▶│
       │                              │ 5. user_transcript event    │
       │                              │    + AbortSignal (TS) /      │
       │                              │    asyncio cancel (Py)       │
       │                              │                              │ 6. LLM call (stream)
       │                              │ 7. session.sendResponse() ◀──│
       │                              │ 8. TTS                       │
       │ 9. WebRTC audio ◀──────────  │                              │
       │                              │                              │
       │ — user interrupts — ───────▶ │                              │
       │                              │ 10. signal aborted /         │
       │                              │     in-flight LLM cancelled  │
       │                              │ 11. new user_transcript ────▶│

The SDK gives you the WebSocket server (speechEngine.attach(), SpeechEngine.Server, Python engine.serve() / engine.create_session()) plus client libraries (@elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native) for the user-facing side.

Speech Engine vs ElevenAgents — pick the right product first

Read the full file on GitHub · 285 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 285 lines · 226 tokens per session scan A 35c4046779ed

Subscribe to this mod's changes

elevenlabs-speech-engine is a skill published in the GitHub repository jakenuts/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 226 tokens to every session and 3,649 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Creative and media

elevenlabs-speech-engine next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
elevenlabs-speech-enginejakenuts/agent-skills	Skill	2	3mo ago	MIT	A	226	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex