Elevenlabs Agents
Configure ElevenLabs conversational voice agents with LLM prompts, TTS/ASR, tools, knowledge base, and multi-language presets.
Overview
Elevenlabs-agents is an agent skill for the Build phase that helps solo builders draft ElevenLabs conversational agent JSON—LLM prompts, TTS/ASR, tools, knowledge base, and workflow nodes—for voice support and assistant
Install
npx skills add https://github.com/jezweb/claude-skills --skill elevenlabs-agentsWhat is this skill?
- Documents `conversation_config` for agent prompt, LLM, temperature, tools, and knowledge base
- TTS block: `eleven_turbo_v2_5`, voice_id, stability, similarity_boost, PCM output formats
- ASR with Deepgram provider, keyword boosting, and turn timeout settings
- Multi-language `language_presets` with per-locale voice and first_message
- Workflow graph nodes (e.g. subagent) for routed conversational flows
Adoption & trust: 1.3k installs on skills.sh; 841 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want a voice AI agent on ElevenLabs but lack a consistent template for prompts, voices, ASR, tools, and multilingual first messages.
Who is it for?
Indie SaaS or support builders adding ElevenLabs-powered phone or web voice agents with LLM tools and KB grounding.
Skip if: Text-only chatbots with no TTS/ASR, or teams not using ElevenLabs’ agent platform.
When should I use this skill?
When designing or implementing ElevenLabs voice agent configurations, TTS/ASR settings, or multilingual conversation presets.
What do I get? / Deliverables
You get a review-ready ElevenLabs agent configuration skeleton you can adapt with real voice IDs, tool IDs, secrets, and workflow nodes before shipping.
- ElevenLabs agent JSON with conversation_config
- Language presets and optional workflow node graph draft
Recommended Skills
Journey fit
This skill is about wiring a third-party voice agent platform during product build—canonical under integrations when you add support or sales voice experiences. ElevenLabs Agents API config (prompt, tools, TTS, ASR, workflows) is external service integration work, not generic frontend styling.
How it compares
Skill package for ElevenLabs agent JSON and conversation_config—not a self-hosted realtime voice MCP server.
Common Questions / FAQ
Who is elevenlabs-agents for?
Solo and indie builders integrating ElevenLabs voice agents who need prompt, TTS, ASR, and workflow configuration guidance in one place.
When should I use elevenlabs-agents?
Use in Build → integrations while defining support or product voice agents, before you connect webhooks, telephony, or production monitoring.
Is elevenlabs-agents safe to install?
The skill references API keys and secrets placeholders—never paste production secrets into prompts; review the Security Audits panel on this page before install.
SKILL.md
READMESKILL.md - Elevenlabs Agents
{ "name": "Support Agent", "conversation_config": { "agent": { "prompt": { "prompt": "You are a helpful customer support agent...", "llm": "gpt-4o-mini", "temperature": 0.7, "max_tokens": 500, "tool_ids": ["tool_123"], "knowledge_base": ["doc_456"], "custom_llm": { "endpoint": "https://api.openai.com/v1/chat/completions", "api_key": "{{secret__openai_api_key}}", "model": "gpt-4" } }, "first_message": "Hello! How can I help you today?", "language": "en" }, "tts": { "model_id": "eleven_turbo_v2_5", "voice_id": "your_voice_id", "stability": 0.5, "similarity_boost": 0.75, "speed": 1.0, "output_format": "pcm_22050" }, "asr": { "quality": "high", "provider": "deepgram", "keywords": ["product_name", "company_name"] }, "turn": { "mode": "normal", "turn_timeout": 5000 }, "conversation": { "max_duration_seconds": 600 }, "language_presets": [ { "language": "en", "voice_id": "en_voice_id", "first_message": "Hello! How can I help you?" }, { "language": "es", "voice_id": "es_voice_id", "first_message": "¡Hola! ¿Cómo puedo ayudarte?" } ] }, "workflow": { "nodes": [ { "id": "node_1", "type": "subagent", "config": { "system_prompt": "You are now handling technical support...", "turn_eagerness": "patient", "voice_id": "tech_voice_id" } }, { "id": "node_2", "type": "tool", "tool_name": "transfer_to_human" } ], "edges": [ { "from": "node_1", "to": "node_2", "condition": "user_requests_escalation" } ] }, "platform_settings": { "widget": { "theme": { "primaryColor": "#3B82F6", "backgroundColor": "#1F2937", "textColor": "#F9FAFB" }, "position": "bottom-right" }, "authentication": { "type": "signed_url", "session_duration": 3600 }, "privacy": { "transcripts": { "retention_days": 730 }, "audio": { "retention_days": 2190 }, "zero_retention": false } }, "webhooks": { "post_call": { "url": "https://api.example.com/webhook", "headers": { "Authorization": "Bearer {{secret__webhook_auth_token}}" } } }, "tags": ["customer-support", "production"] } name: Deploy ElevenLabs Agent on: push: branches: [main] paths: - 'agent_configs/**' - 'tool_configs/**' - 'test_configs/**' pull_request: branches: [main] jobs: test: runs-on: ubuntu-latest steps: - uses: actions/checkout@v3 - name: Setup Node.js uses: actions/setup-node@v3 with: node-version: '18' - name: Install ElevenLabs CLI run: npm install -g @elevenlabs/cli - name: Dry Run (Preview Changes) run: elevenlabs agents push --env staging --dry-run env: ELEVENLABS_API_KEY: ${{ secrets.ELEVENLABS_API_KEY_STAGING }} - name: Push to Staging if: github.event_name == 'pull_request' run: elevenlabs agents push --env staging env: ELEVENLABS_API_KEY: ${{ secrets.ELEVENLABS_API_KEY_STAGING }} - name: Run Tests if: github.event_name == 'pull_request' run: | elevenlabs tests push --env staging elevenlabs agents test "Support Agent" env: ELEVENLABS_API_KEY: ${{ secrets.ELEVENLABS_API_KEY_STAGING }} deploy: runs-on: ubuntu-latest needs: test if: github.ref == 'refs/heads/main' && github.event_name == 'push' steps: - uses: actions/checkout@v3 - name: Setup Node.js uses: actions/setup-node@v3 with: nod