ElevenLabs Conversational AI (ElevenAgents)

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)

Pricing model

Hybrid (base + usage) [2]elevenlabs.io/pricing/agents“Free: $0/month, 15 min included; Starter: $6/month, 75 min; Creator: $22/month, 275 min; Pro: $99/month, 1,238 min; Scale: $299/month, 3,738 min; Business: $990/month, 12,375 min. Additional Call (per minute) $0.003; Included Call (per minute) $0.080.”

Published pricing

✓ Yes

Free tier

✓ Yes [3]elevenlabs.io/pricing/agents“Free: $0/month — 15 minutes included, 4 concurrent calls, Workflow Builder, Knowledge Base, multilingual support, Widget.”

Free tier details

Free plan at $0/month includes 15 minutes of agent calls per month, up to 4 concurrent calls, Workflow Builder, Knowledge Base, multilingual support, and web widget.

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes [4]elevenlabs.io/pricing/agents“Enterprise: Custom pricing with elevated concurrency, custom DPA/SLA terms, HIPAA BAAs, custom SSO, and priority support.”

• Outbound calling
• BYO models
• Multilingual

Supported actions

realtime_conversation, inbound_telephony, outbound_telephony, sip_trunking, function_calling, tool_calling, interruption_handling, byo_llm, byo_voice, knowledge_base, batch_calling, call_recording, web_widget, call_transfer, webhooks, a_b_testing, rag_knowledge_base, dynamic_variables [5]elevenlabs.io/docs/eleven-agents/overview“SIP trunk integration with existing phone infrastructure; Programmatic batch outbound calling; Native Twilio integration for phone communications; Tool integration enabling agents to call clients & APIs to perform actions; Choose from supported LLMs or bring your own custom model.”elevenlabs.io/docs/eleven-agents/overview“Multi-step conversation workflows with visual builder; Real-time event subscription and conversation monitoring; A/B testing and automated agent behavior testing; Per-conversation personalization via dynamic variables.”

Regions

United States, European Union, India, Singapore [6]elevenlabs.io/docs/overview/administration/data-residency“ElevenLabs offers data residency in four locations: US (default), EU (api.eu.residency.elevenlabs.io), India (api.in.residency.elevenlabs.io), and Singapore (api.sg.residency.elevenlabs.io).”

Languages

English, Japanese, Chinese, German, Hindi, French, Korean, Portuguese, Italian, Spanish, Indonesian, Dutch, Turkish, Filipino, Polish, Swedish, Bulgarian, Romanian, Arabic, Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Tamil, Ukrainian, Russian, Hungarian, Norwegian, Vietnamese [7]elevenlabs.io/docs/eleven-agents/overview“For real-time conversational applications, you should use eleven_flash_v2_5, eleven_flash_v2 or eleven_multilingual_v2.”elevenlabs.io/docs/overview/models“Flash v2.5 supports 32 languages: All languages from v2 models plus Hungarian, Norwegian & Vietnamese. Multilingual v2 supports 29 languages: English (USA, UK, Australia, Canada), Japanese, Chinese, German, Hindi, French (France, Canada), Korean, Portuguese (Brazil, Portugal), Italian, Spanish (Spain, Mexico), Indonesian, Dutch, Turkish, Filipino, Polish, Swedish, Bulgarian, Romanian, Arabic (Saudi Arabia, UAE), Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Tamil, Ukrainian & Russian.”

Input types

PSTN phone call, SIP trunk, WebRTC, web widget, text/chat [8]elevenlabs.io/docs/eleven-agents/overview“ElevenLabs Conversational AI enables real-time, bi-directional audio streaming for use cases like PSTN calls, SIP trunks, and WebRTC clients.”

Output types

audio stream, call transcript, webhook events, structured call summary, conversation analytics

Webhooks

✓ Yes

Sandbox / test mode

✗ No

SDK languages

Python, TypeScript/JavaScript, TypeScript/JavaScript (Agents client), React, React Native, Kotlin/Android [9]elevenlabs.io/docs/eleven-agents/overview“SDK Languages: React (web apps and hooks/components), Swift (native iOS), Kotlin (native Android), React Native (cross-platform mobile), WebSocket API (custom implementations).”elevenlabs.io/docs/overview/intro“REST interface with official Python and TypeScript SDKs.”

MCP server

✓ Yes [10]github.com/elevenlabs/elevenlabs-mcp“The official ElevenLabs MCP server (pip install elevenlabs-mcp).”

SOC 2

SOC 2 Type II [11]compliance.elevenlabs.io“ElevenLabs Trust Center lists SOC 2 Type II, ISO 27001, and PCI DSS Level 1 certifications.”elevenlabs.io/agents/ai-trust-and-reliability“The platform maintains the following certifications: SOC 2 Type II, ISO 27001, PCI DSS Level 1, HIPAA attestation, GDPR attestation.”

HIPAA

✓ Yes [12]elevenlabs.io/agents/ai-trust-and-reliability“HIPAA attestation.”elevenlabs.io/enterprise“HIPAA-eligible configurations available with Zero Retention Mode enabled and a Business Associate Agreement (BAA) in place.”

GDPR

✓ Yes [13]elevenlabs.io/docs/overview/administration/data-residency“The platform implements measures to align with applicable GDPR requirements, including measures designed to ensure lawful data processing, adherence to data subject rights, and the implementation of appropriate security measures.”

ISO 27001

✓ Yes [14]elevenlabs.io/agents/ai-trust-and-reliability“ISO 27001.”compliance.elevenlabs.io“ElevenLabs also holds ISO 27001/17/18, ISO 27701, and ISO 42001 certificates, along with Cyber Essentials Plus Certification.”

PCI DSS

✓ Yes [15]elevenlabs.io/agents/ai-trust-and-reliability“PCI DSS Level 1.”

Published SLA

✗ No [16]elevenlabs.io/enterprise“Custom service-level agreements available for mission-critical workloads — no standard published SLA percentages found on any public page.”

Rate limits

Concurrency limits by plan: Free=4, Starter=6, Creator=10, Pro=20, Scale=30, Business=40, Enterprise=custom/elevated. Burst pricing allows up to 3x normal concurrency at $0.160/min (double the standard included rate). [17]elevenlabs.io/pricing/agents“Free: 4 concurrent calls; Starter: 6 concurrent calls; Creator: 10 concurrent calls; Pro: 20 concurrent calls; Scale: 30 concurrent calls; Business: 40 concurrent calls. Burst pricing: $0.160/minute (enables up to 3x normal concurrency at double the standard rate).”

Known restrictions

LLM costs are currently absorbed by ElevenLabs but will eventually be passed on to customers, Telephony provider costs (Twilio, Telnyx, etc.) billed separately at actual usage rates, EU data residency requires Zero Retention Mode and direct API use (no custom LLMs or webhooks with out-of-region processing), HIPAA BAA available only on Enterprise plan, Custom SSO available only on Enterprise plan, Dubbing functionality unavailable in isolated regional environments [18]elevenlabs.io/docs/overview/administration/data-residency“Dubbing functionality is currently unavailable in isolated environments, and model availability varies by region depending on provider support.”elevenlabs.io/blog/we-cut-our-pricing-for-conversational-ai“The above prices do not include LLM costs. We're currently absorbing those fees though will eventually pass those costs on.”

• Docs
• API reference
• llms.txt
• Changelog
• Status page

Docs rendering: static · llms.txt present

API style

websocket

Base URL

https://api.elevenlabs.io/v1

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key

Idempotency keys

✗ No

Error format

vendor-specific JSON with top-level "detail" object containing type, code, message, status, request_id, param fields

Webhook signing

hmac

Rate limit

4 / concurrent calls

SDKs

• Python elevenlabs · repo
• TypeScript/JavaScript @elevenlabs/elevenlabs-js · repo
• TypeScript/JavaScript (Agents client) @elevenlabs/client · repo
• React @elevenlabs/react · repo
• React Native @elevenlabs/react-native · repo
• Kotlin/Android elevenlabs-android · repo

• Auth docs
• Quickstart
• MCP server
• Webhook events
• Deprecation policy

Launched

2024-11-11

GA

2024-11-11

Notable customers

Revolut, Deliveroo, Epic Games, Deutsche Telekom, Klarna, Meesho, Cisco, NVIDIA, TELUS Digital, Bertelsmann

• OpenAI Realtime API (gpt-realtime)

  "The Realtime API enables low-latency, bidirectional audio communication for building voice agents and audio applications."

  Usage · public pricing · self-serve

• Telnyx Voice AI Agents

  "Carrier-grade Voice AI from Telnyx. Sub-200ms latency, 80+ languages, A-level STIR/SHAKEN attestation, and one platform that replaces 5 vendors."

  Usage · public pricing · self-serve

• Twilio ConversationRelay

  "Twilio's Conversation Relay empowers you to build powerful AI voice experiences for your customers. Let Twilio handle the heavy lifting of speech recognition, text-to-speech, and voice synthesis."

  Usage · public pricing · self-serve

• Vapi

  "Build and deploy voice agents that deliver the outcomes you want at the scale your customers need."

  Usage · free tier · public pricing · self-serve

• Cartesia Line

  "Turn any text agent into a world-class conversational agent, deployed anywhere."

  Hybrid · free tier · public pricing · self-serve

• Pipecat Cloud (Daily)

  "The fastest path to production voice AI" - a managed hosting platform for deploying and scaling Pipecat agents in production with built-in infrastructure.

  Usage · public pricing · self-serve

ElevenLabs Conversational AI (ElevenAgents) alternatives · ElevenLabs Conversational AI (ElevenAgents) vs OpenAI Realtime API (gpt-realtime) · All Realtime Voice Agent APIs APIs

Each field above carries a numbered source - hover for a preview, click to jump here.

1. ↑Description: elevenlabs.io
2. ↑Pricing model: elevenlabs.io
3. ↑Free tier: elevenlabs.io
4. ↑Enterprise plan: elevenlabs.io
5. ↑Supported actions: elevenlabs.io · elevenlabs.io
6. ↑Regions: elevenlabs.io
7. ↑Languages: elevenlabs.io · elevenlabs.io
8. ↑Input types: elevenlabs.io
9. ↑SDK languages: elevenlabs.io · elevenlabs.io
10. ↑MCP server: github.com
11. ↑SOC 2: compliance.elevenlabs.io · elevenlabs.io
12. ↑HIPAA: elevenlabs.io · elevenlabs.io
13. ↑GDPR: elevenlabs.io
14. ↑ISO 27001: elevenlabs.io · compliance.elevenlabs.io
15. ↑PCI DSS: elevenlabs.io
16. ↑Published SLA: elevenlabs.io
17. ↑Rate limits: elevenlabs.io
18. ↑Known restrictions: elevenlabs.io · elevenlabs.io

Every field change, who made it, and when - from our audited data pipeline and editors.

1. 2026-06-21 Capabilities: {} → {"byo_models":true,"multilingual":true,"outbound_calling":true}
2. 2026-06-21 Summary Md: (none) → ElevenLabs Conversational AI (ElevenAgents) is a real-time voice agent platform…
3. 2026-06-21 Score Pricing Transparency: (none) → 100
4. 2026-06-21 Score Setup Speed: (none) → 85
5. 2026-06-21 Score Docs Quality: (none) → 55
6. 2026-06-21 Score Procurement Friction: (none) → 100
7. 2026-06-21 Score Trust Readiness: (none) → 80
8. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
9. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
10. 2026-06-21 Score Agent Friendliness: (none) → 65
11. 2026-06-21 Llms Txt Present: (none) → Yes
12. 2026-06-21 Changelog URL: (none) → https://elevenlabs.io/changelog
13. 2026-06-21 Docs URL: (none) → https://elevenlabs.io/docs/overview/intro
14. 2026-06-21 Llms Txt URL: (none) → https://elevenlabs.io/llms.txt
15. 2026-06-21 Rendering: (none) → static
16. 2026-06-21 Has Structured Data: (none) → Yes
17. 2026-06-21 Robots Allows Agents: (none) → Yes
18. 2026-06-21 API Reference URL: (none) → https://elevenlabs.io/api
19. 2026-06-21 Status Page URL: (none) → https://status.elevenlabs.io
20. 2026-06-21 Free Tier Available: set to Yes
21. 2026-06-21 Free Tier Details: set to Free plan at $0/month includes 15 minutes of agent calls per month, up to 4 con…
22. 2026-06-21 Self Serve Signup: set to Yes
23. 2026-06-21 Requires Sales Call: set to No
24. 2026-06-21 Enterprise Plan Available: set to Yes
25. 2026-06-21 SOC 2: set to type_2
26. 2026-06-21 HIPAA: set to Yes
27. 2026-06-21 GDPR: set to Yes
28. 2026-06-21 ISO 27001: set to Yes
29. 2026-06-21 PCI DSS: set to Yes
30. 2026-06-21 SLA Published: set to No
31. 2026-06-21 Data Retention Policy URL: set to https://elevenlabs.io/docs/eleven-api/resources/zero-retention-mode
32. 2026-06-21 Documented Rate Limits: set to Concurrency limits by plan: Free=4, Starter=6, Creator=10, Pro=20, Scale=30, Bu…
33. 2026-06-21 Rate Limit Requests: set to 4
34. 2026-06-21 Rate Limit Window: set to concurrent calls
35. 2026-06-21 Known Restrictions: set to LLM costs are currently absorbed by ElevenLabs but will eventually be passed on…
36. 2026-06-21 Auth Methods: set to api_key
37. 2026-06-21 Auth Docs URL: set to https://elevenlabs.io/docs/api-reference/authentication
38. 2026-06-21 API Style: set to websocket
39. 2026-06-21 Base URL: set to https://api.elevenlabs.io/v1
40. 2026-06-21 API Version: set to v1
41. 2026-06-21 Versioning Scheme: set to url
42. 2026-06-21 Stability: set to ga
43. 2026-06-21 Deprecation Policy URL: set to https://elevenlabs.io/docs/developers/best-practices/breaking-changes-policy
44. 2026-06-21 MCP URL: set to https://github.com/elevenlabs/elevenlabs-mcp
45. 2026-06-21 Quickstart URL: set to https://elevenlabs.io/docs/eleven-agents/quickstart
46. 2026-06-21 Idempotency Supported: set to No
47. 2026-06-21 Error Format: set to vendor-specific JSON with top-level "detail" object containing type, code, mess…
48. 2026-06-21 Webhook Signing: set to hmac
49. 2026-06-21 Webhook Events URL: set to https://elevenlabs.io/docs/eleven-api/resources/webhooks
50. 2026-06-21 Requires Verification: set to No

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

curl -X POST https://apio.sh/api/feedback/elevenlabs-agents \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/elevenlabs-agents/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →