Compare Lab
Cartesia vs LiveKit
Cartesia is positioned as speech models for teams assembling a voice stack, with a separate managed-agent product. LiveKit is positioned as realtime agent infrastructure for teams that own the application and model stack. Start by
Cartesia is positioned as speech models for teams assembling a voice stack, with a separate managed-agent product. LiveKit is positioned as realtime agent infrastructure for teams that own the application and model stack. Start by deciding who owns the missing layers, then inspect the documented differences below.
Voice Engines and Developer Frameworks are different product categories. An underlying engine or framework is not a complete substitute for a deployed agent workflow.
13 jointly documented catalog fields. This measures evidence coverage, not equivalent quality or an overall winner.
Test opening hours, booking conflicts and an unanswered transfer.
Start where the records differ.
Values and evidence states are compared together. Shared facts follow the differences; Unknown never means No.
| Decision point | Cartesia | LiveKit |
|---|---|---|
| Billing unitDifferent records | TTS/STT credits; Managed Agents conversation minutes | Plan/month + agent minutes + telephony minutes + inference tokens/characters/audio + observability entries |
| Bring your modelDifferent records | Yes | Yes |
| Warm transferDifferent records | Unknown | Yes |
| HIPAA pathDifferent records | Yes | Yes |
| WebhooksDifferent records | YesAPI / webhook | YesUnknown |
| Billing modelShared state | component-stack | component-stack |
Your requirements & next steps
Your requirements
Ready-made / AI receptionist · Strict evidence mode
No personal requirements yet. Add criteria in Advanced Filter to prioritize this comparison.
TTS/STT credit subscriptions and Managed Agents minute charges remain separate.
Plan plus session, telephony, inference, observability and other usage; example calculator minute total is not fixed price.
Speech model credits and selected LLM/evaluation charges have separate scope.
Agent session component only; not complete call cost.
Product-specific units preserved.
No universal conversion of model inference to minute rate.
Plan allowances include separate agent prepayment; do not double-count as universal included voice minutes.
Usage overages and model inference additional.
Separate credit and agent budgets; no arbitrary cross-product minute conversion.
Separate allowance buckets; no implied complete free call quantity.
Free allowances and product rates are available; old changelog, bandwidth trial and speech volume controls do not establish these current billing terms.
Build allowances are hard caps; paid usage beyond allowances is incremental, not a complete price/minute.
LLM promotion ends October 1, 2026; quoted model/usage mix determines bill.
Usage mix and selected providers required.
Not yet researched against this buyer-critical field standard.
Not yet researched against this buyer-critical field standard.
Product mix, LLM promotion expiry, carrier routing and other metered components prevent a universal all-in ceiling.
The calculator example $0.0479/min is assumption-specific; no maximum complete bill from minutes alone.
Product mix, LLM promotion expiry, carrier routing and other metered components prevent a universal all-in ceiling.
The calculator example $0.0479/min is assumption-specific; no maximum complete bill from minutes alone.
Anyone with this link can view the encoded decision criteria.
Vendor documentation establishes a claim. Public model benchmarks are separate context, not measurements of these platforms.
Open saved comparison ↗What to verify together.
Cartesia
A speech credit plan is not a complete phone-call bill.
Managed Agents $0.06/min; Cartesia-provided-number telephony $0.014/min · V3.3 evidence review · Managed Agents base rate; carrier/model charges and prepaid plan balances separate
Excluded / confirm: Complete cost cannot be established from this reference. Product mix, LLM promotion expiry, carrier routing and other metered components prevent a universal all-in ceiling. · LLM tokens after promotional coverage; telephony and evaluation usage
TTS/STT credit subscriptions and Managed Agents minute charges remain separate.
LiveKit
Agent-session pricing excludes a complete inference and telephony stack.
Paid Cloud agent sessions $0.01/min beyond allowance · V3.3 evidence review · Cloud Ship starting subscription; session overage, inference, transport and artifacts extra
Excluded / confirm: Complete cost cannot be established from this reference. The calculator example $0.0479/min is assumption-specific; no maximum complete bill from minutes alone. · Inference, phone number/transport, recording and observability, outbound carrier, bandwidth and optional private links
Plan plus session, telephony, inference, observability and other usage; example calculator minute total is not fixed price.
The evidence overlap.
Both records have documented values for Product type, Technical setup, Pricing model, Published numeric pricing, Free tier, Cartesia TTS, Realtime / streaming audio, Function / tool calling, Published included concurrency at least, Local number availability, Official product documentation, Checked within 30 days and additional fields shown in Compare. Matching availability does not measure behavior under your call conditions.
Run the same booking, tool failure and unsuccessful human-transfer cases. Record both outcomes and billable units before signing a deployment agreement.
Build a buyer-operated pilot →