Compare Lab
Deepgram vs Retell AI
Deepgram is positioned as speech recognition models with separate speech generation and managed voice-agent APIs. Retell AI is positioned as a configurable call-agent platform with visual flows, APIs and integrated call operations
Deepgram is positioned as speech recognition models with separate speech generation and managed voice-agent APIs. Retell AI is positioned as a configurable call-agent platform with visual flows, APIs and integrated call operations. Start by deciding who owns the missing layers, then inspect the documented differences below.
STT and Full Platforms are different product categories. An underlying engine or framework is not a complete substitute for a deployed agent workflow.
19 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 | Retell AI |
|---|---|---|
| Billing unitDifferent records | STT audio minute; TTS thousand characters; agent WebSocket connection minute | minute |
| Bring your telephonyDifferent records | Yes | Yes |
| Warm transferDifferent records | Unknown | Yes |
| WebhooksDifferent records | YesUnknown | YesAPI / webhook |
| Billing modelShared state | component-stack | component-stack |
| 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.
Reviewed current public offer; retain original billing scope and units.
External provider and telephony bills excluded where applicable. Do not infer a complete monthly ceiling.
Reviewed current public offer; retain original billing scope and units.
Billable open connection time is not just spoken audio.
Reviewed current public offer; retain original billing scope and units.
Growth is annual prepaid commitment, not invented monthly subscription.
Zero platform fee is not zero total fixed cost.
No fixed included agent minutes inferred from credit dollars.
Paid extras$8/slot/month and$8/KB/month; usage separate.
Initial credits, Growth commitments and tier rates are documented; no recurring free plan or universal rounding/contract terms inferred.
Reviewed current public offer; retain original billing scope and units.
Agent pricing covers selected tier and components; full workload determines bill.
Reviewed current public offer; retain original billing scope and units.
Not yet researched against this buyer-critical field standard.
Reviewed current public offer; retain original billing scope and units.
Carrier, hosting, model tier and BYO usage prevent a universal full monthly or per-minute ceiling.
A headline configuration range is not a ceiling on telephony, model, add-on or burst charges.
Carrier, hosting, model tier and BYO usage prevent a universal full monthly or per-minute ceiling.
Research conclusion about cost completeness, not a vendor capability.
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.
Retell AI
The advertised price band is not a ceiling for every model configuration.
Voice-agent configuration range $0.07–$0.31/min · V3.3 evidence review · Published configured-agent range lower reference; not a guaranteed all-in floor or ceiling
Excluded / confirm: Complete cost cannot be established from this reference. A headline configuration range is not a ceiling on telephony, model, add-on or burst charges. · Telephony, selected LLM/TTS, add-ons and concurrency burst can add charges
Reviewed current public offer; retain original billing scope and units.
The evidence overlap.
Both records have documented values for Product type, Technical setup, Pricing model, Published numeric pricing, Twilio, Cartesia TTS, OpenAI models, Anthropic models, Google models, Bring your model, Function / tool calling, Interruption controls 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 →