Cartesia Line

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]cartesia.ai/pricing“Free $0/mo; Pro $5/mo; Startup $49/mo; Scale $299/mo; Enterprise Custom. Call duration: $0.06 per minute. Telephony: $0.014 per minute when using a Cartesia-provided phone number.”cartesia.ai/pricing“Free: 20K credits/month + $1 prepaid agents/month; Pro: 100K credits/month + $5 prepaid agents/month; Startup: 1.25M credits/month + $49 prepaid agents/month; Scale: 8M credits/month + $299 prepaid agents/month”

Published pricing

✓ Yes

Free tier

✓ Yes [3]cartesia.ai/pricing“Free $0/mo — 20K credits / month, $1 prepaid agents/month, 1 agent slot, 8 concurrent calls. Start free. Pause or cancel anytime.”

Free tier details

Free plan at $0/month with 20K credits/month and $1/month prepaid agent budget; 1 voice agent slot; 8 concurrent calls. Voice agent call duration billed at $0.06/minute; telephony $0.014/minute for Cartesia phone numbers.

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes [4]cartesia.ai/pricing“Enterprise Plan - Custom pricing and volume-based rates - Requires contacting sales - Includes DPAs, BAAs, SSO, and security features”

• Built-in telephony
• Outbound calling
• BYO models
• No-code builder

Supported actions

realtime_conversation, inbound_telephony, outbound_telephony, sip_trunking, call_transfer, function_calling, tool_calling, interruption_handling, byo_llm, knowledge_base, batch_calling, call_recording, webhooks, multi_agent_handoff, web_search_tool, dtmf_support, send_dtmf, agent_builder_no_code, websocket_audio_streaming, custom_pronunciations, ambient_audio, call_transcripts, observability_metrics, http_server_tool, post_call_analysis [5]docs.cartesia.ai/line/infrastructure/observability“Supported webhook events: call_started, call_completed, call_failed, call_turn, post_call_analysis”docs.cartesia.ai/line/sdk/tools“end_call: Ends the call and disconnects; transfer_call: Transfers to another phone number in E.164 format; web_search: Retrieves real-time information from the internet; knowledge_base: Searches attached documents; send_dtmf: Sends DTMF tones during calls; agent_as_handoff: Creates a handoff tool from another agent, enabling multi-agent workflows; http_server_tool: Calls REST APIs via JSON schemas”

Regions

United States (Cartesia Numbers), Any country available in Twilio (via Twilio integration)

Languages

English (US), English (GB), English (Canada), English (New Zealand), English (South Africa), Spanish (Mexico), Spanish, German, French, French (Canada), Italian, Hindi, Mandarin Chinese, Brazilian Portuguese, Arabic (UAE), Hebrew, Thai, 40+ languages via Sonic TTS [6]cartesia.ai/sonic“40+ languages and a wide range of accents, all with native-speaker quality voices”

Input types

PSTN phone call, audio stream (WebSocket), SIP (beta) [7]docs.cartesia.ai/line/integrations/telephony/phone-numbers“Cartesia Numbers: US only provisioning; Twilio Numbers: Support extends globally to any country available in Twilio”docs.cartesia.ai/line/integrations/websocket-api“wss://api.cartesia.ai/agents/stream/{agent_id} — The WebSocket connection uses JSON messages for control events and base64-encoded audio for media. Input formats: mulaw_8000, pcm_16000, pcm_24000, pcm_44100.”

Output types

audio stream, call transcript, webhook events, call recording, observability metrics, call summary, post-call analysis

Webhooks

✓ Yes [8]docs.cartesia.ai/line/infrastructure/observability“Cartesia enables webhook integration for call monitoring. Webhooks require HTTPS endpoint accepting POST requests with application/json. Secret verification via the x-webhook-secret header.”

Sandbox / test mode

✗ No

SDK languages

Python (Line SDK), Python (inference SDK), JavaScript/TypeScript [9]github.com/cartesia-ai/cartesia-js“The JavaScript client for the Cartesia API. npm install @cartesia/cartesia-js”github.com/cartesia-ai/line“Line is a Python SDK for building intelligent, low-latency voice agents. Package: cartesia-line. Installation: uv add cartesia-line”

MCP server

✗ No

SOC 2

SOC 2 Type II [10]cartesia.ai/agents“SOC 2 Type 2 certified”cartesia.ai/blog/gdpr-compliance“SOC 2 Type II, PCI-DSS (service level provider), HIPAA, and optional Zero Data Retention — Listed among security foundations”

HIPAA

✓ Yes [11]cartesia.ai/agents“HIPAA compliant”cartesia.ai/blog/gdpr-compliance“SOC 2 Type II, PCI-DSS (service level provider), HIPAA, and optional Zero Data Retention”

GDPR

✓ Yes [12]cartesia.ai/blog/gdpr-compliance“our text-to-speech platform is now GDPR compliant”cartesia.ai/legal/dpa“Service Provider shall comply with the obligations of Applicable Data Protection Laws”

ISO 27001

– Unknown [13]cartesia.ai/blog/gdpr-compliance“SOC 2 Type II, PCI-DSS (service level provider), HIPAA, and optional Zero Data Retention — ISO 27001 not mentioned in this compliance listing”

PCI DSS

✓ Yes [14]cartesia.ai/blog/gdpr-compliance“PCI-DSS (service level provider)”

Published SLA

✗ No [15]status.cartesia.ai“Voice Agents: 99.89% uptime — status page shows historical metrics only; no published SLA, contractual uptime guarantee, or penalty clause language found”

Rate limits

Outbound calling: 1 call per second; Concurrent calls by plan: Free=8, Pro=12, Startup=20, Scale=60. Batch calling: up to 1,000 recipients per batch. Agent compute: 1GB memory and 0.5 vCPU per call (higher on request). [16]docs.cartesia.ai/line/infrastructure/scaling“Each API call receives 1GB of memory and 0.5 vCPU.”docs.cartesia.ai/line/infrastructure/scaling“Concurrency Limits: Free=8, Pro=12, Startup=20, Scale=60 concurrent calls. When triggering outbound calls, you are limited to triggering one call per second.”

Known restrictions

Cartesia-provisioned phone numbers are US-only; international coverage requires BYO Twilio account, SIP trunking is in Beta (early access, contact support@cartesia.ai), No dedicated sandbox/test environment documented, BYO-voice (custom voice upload for TTS) not supported - uses Cartesia Sonic voice library only, Outbound calls limited to 1 per second rate [17]docs.cartesia.ai/line/integrations/telephony/phone-numbers“Cartesia Numbers: US only — all Cartesia-managed numbers are from the US. Twilio numbers: pay your Twilio usage rates directly to Twilio based on actual usage.”

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

Docs rendering: static · markdown variants served · llms.txt present

API style

websocket

Base URL

https://api.cartesia.ai

Version

2025-04-16

Versioning

header

Stability

ga

Auth methods

api_key

Error format

vendor-specific JSON (error_code, title, message, request_id, optional doc_url) for Cartesia-Version >= 2026-03-01; legacy plain-text for earlier versions

Rate limit

60 / concurrent calls

SDKs

• Python (Line SDK) cartesia-line · repo
• Python (inference SDK) cartesia · repo
• JavaScript/TypeScript @cartesia/cartesia-js · repo

• Auth docs
• Quickstart

Launched

2025-08-19

GA

2025-08-19

Notable customers

ServiceNow, Maven AGI, Retell, Vapi, LiveKit, Replicant, Thoughtly, Cresta, Quora

• ElevenLabs Conversational AI (ElevenAgents)

  "Deploy human-like Conversational AI in minutes. ElevenLabs delivers low latency interactions in dozens of languages with enterprise-grade security."

  Hybrid · free tier · public pricing · self-serve

• 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

• 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

Cartesia Line alternatives · Cartesia Line vs ElevenLabs Conversational AI (ElevenAgents) · All Realtime Voice Agent APIs APIs

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

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

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

1. 2026-06-21 Score Agent Friendliness: 20 → 55
2. 2026-06-21 Score Docs Quality: 15 → 70
3. 2026-06-21 Best For: Prototypes and side projects - free to start, no sales call, Regulated or enter… → Prototypes and side projects - free to start, no sales call, Regulated or enter…
4. 2026-06-21 API Reference URL: (none) → https://docs.cartesia.ai/use-the-api/api-conventions
5. 2026-06-21 Has Structured Data: (none) → Yes
6. 2026-06-21 Rendering: (none) → static
7. 2026-06-21 Markdown Docs URL: (none) → https://docs.cartesia.ai/get-started/overview.md
8. 2026-06-21 Llms Txt Present: No → Yes
9. 2026-06-21 Llms Txt URL: (none) → https://docs.cartesia.ai/llms.txt
10. 2026-06-21 Markdown Docs Served: (none) → Yes
11. 2026-06-21 Changelog URL: (none) → https://docs.cartesia.ai/changelog
12. 2026-06-21 Capabilities: {} → {"byo_models":true,"no_code_builder":true,"outbound_calling":true,"telephony_in…
13. 2026-06-21 Summary Md: (none) → Cartesia Line is a telephony platform for building and deploying AI voice agent…
14. 2026-06-21 Score Agent Friendliness: (none) → 20
15. 2026-06-21 Score Pricing Transparency: (none) → 100
16. 2026-06-21 Score Setup Speed: (none) → 85
17. 2026-06-21 Score Docs Quality: (none) → 15
18. 2026-06-21 Score Procurement Friction: (none) → 100
19. 2026-06-21 Score Trust Readiness: (none) → 65
20. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
21. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
22. 2026-06-21 Docs URL: (none) → https://docs.cartesia.ai/get-started/overview
23. 2026-06-21 Llms Txt Present: (none) → No
24. 2026-06-21 Robots Allows Agents: (none) → Yes
25. 2026-06-21 Status Page URL: (none) → https://status.cartesia.ai
26. 2026-06-21 MCP Server Available: set to No
27. 2026-06-21 Pricing Model: set to hybrid
28. 2026-06-21 Has Published Pricing: set to Yes
29. 2026-06-21 Free Tier Available: set to Yes
30. 2026-06-21 Free Tier Details: set to Free plan at $0/month with 20K credits/month and $1/month prepaid agent budget;…
31. 2026-06-21 Self Serve Signup: set to Yes
32. 2026-06-21 Requires Sales Call: set to No
33. 2026-06-21 Enterprise Plan Available: set to Yes
34. 2026-06-21 SOC 2: set to type_2
35. 2026-06-21 HIPAA: set to Yes
36. 2026-06-21 GDPR: set to Yes
37. 2026-06-21 PCI DSS: set to Yes
38. 2026-06-21 SLA Published: set to No
39. 2026-06-21 Data Retention Policy URL: set to https://cartesia.ai/legal/privacy.html
40. 2026-06-21 Documented Rate Limits: set to Outbound calling: 1 call per second; Concurrent calls by plan: Free=8, Pro=12, …
41. 2026-06-21 Rate Limit Requests: set to 60
42. 2026-06-21 Rate Limit Window: set to concurrent calls
43. 2026-06-21 Known Restrictions: set to Cartesia-provisioned phone numbers are US-only; international coverage requires…
44. 2026-06-21 Auth Methods: set to api_key
45. 2026-06-21 Auth Docs URL: set to https://docs.cartesia.ai/use-the-api/api-conventions
46. 2026-06-21 API Style: set to websocket
47. 2026-06-21 Base URL: set to https://api.cartesia.ai
48. 2026-06-21 API Version: set to 2025-04-16
49. 2026-06-21 Versioning Scheme: set to header
50. 2026-06-21 Stability: set to ga

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/cartesia-line \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/cartesia-line/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 →