Compare Lab
Deepgram vs LiveKit
Deepgram is positioned as speech recognition models with separate speech generation and managed voice-agent APIs. LiveKit is positioned as realtime agent infrastructure for teams that own the application and model stack. Start by
Deepgram is positioned as speech recognition models with separate speech generation and managed voice-agent APIs. 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.
STT and Developer Frameworks are different product categories. An underlying engine or framework is not a complete substitute for a deployed agent workflow.
20 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 | Deepgram | LiveKit |
|---|---|---|
| Billing unitDifferent records | STT audio minute; TTS thousand characters; agent WebSocket connection minute | Plan/month + agent minutes + telephony minutes + inference tokens/characters/audio + observability entries |
| Warm transferDifferent records | Unknown | Yes |
| HIPAA pathDifferent records | Yes | Yes |
| Billing modelShared state | component-stack | component-stack |
| Bring your telephonyShared state | Yes | Yes |
| Bring your modelShared state | Yes | Yes |
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.
STT audio minutes, TTS characters and Voice Agent connection minutes are distinct.
Plan plus session, telephony, inference, observability and other usage; example calculator minute total is not fixed price.
External provider and telephony bills excluded where applicable. Do not infer a complete monthly ceiling.
Agent session component only; not complete call cost.
Billable open connection time is not just spoken audio.
No universal conversion of model inference to minute rate.
Growth is annual prepaid commitment, not invented monthly subscription.
Usage overages and model inference additional.
No fixed included agent minutes inferred from credit dollars.
Separate allowance buckets; no implied complete free call quantity.
Initial credits, Growth commitments and tier rates are documented; no recurring free plan or universal rounding/contract terms inferred.
Build allowances are hard caps; paid usage beyond allowances is incremental, not a complete price/minute.
Agent pricing covers selected tier and components; full workload 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.
Carrier, hosting, model tier and BYO usage prevent a universal full monthly or per-minute ceiling.
The calculator example $0.0479/min is assumption-specific; no maximum complete bill from minutes alone.
Carrier, hosting, model tier and BYO usage prevent a universal full monthly or per-minute 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.
Deepgram
The current Nova-3 streaming rate is promotional.
Voice Agent Standard $0.075/min; BYO TTS $0.065/min; BYO LLM + TTS $0.050/min; Advanced $0.163/min (PAYG) · V3.3 evidence review · Voice Agent Standard PAYG WebSocket connection minutes; other tiers/BYO variants differ
Excluded / confirm: Complete cost cannot be established from this reference. Carrier, hosting, model tier and BYO usage prevent a universal full monthly or per-minute ceiling. · BYO model/TTS charges, carrier and customer transport hosting
STT audio minutes, TTS characters and Voice Agent connection minutes are distinct.
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, Twilio, Bring your TTS, Cartesia TTS, Realtime / streaming audio, Deepgram STT, OpenAI models, Anthropic models, Google models 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 →