Compare Lab
Hume AI vs OpenAI Realtime API
Hume AI is positioned as hume TTS and EVI API sunset: announced access end November 13, 2026 at 05:01 UTC. Retained for historical comparison and migration research. OpenAI Realtime API is positioned as speech-to-speech API for de
Hume AI is positioned as hume TTS and EVI API sunset: announced access end November 13, 2026 at 05:01 UTC. Retained for historical comparison and migration research. OpenAI Realtime API is positioned as speech-to-speech API for developers implementing their own voice application. 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.
10 jointly documented catalog fields. This measures evidence coverage, not equivalent quality or an overall winner.
TTS + EVI API sunset · Announced end: 13 Nov 2026, 05:01 UTC. Read notice & sources →
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 | Hume AI | OpenAI Realtime API |
|---|---|---|
| Billing modelDifferent records | monthly-bundle | component-stack |
| Billing unitDifferent records | Monthly subscription + EVI minutes / TTS characters / supplemental LLM usage | 1 million text/audio/image tokens; transcription separately metered |
| Bring your telephonyDifferent records | Yes | Yes |
| Bring your modelDifferent records | Yes | Unknown |
| HIPAA pathDifferent records | Yes | Unknown |
| WebhooksDifferent records | YesAPI / webhook | YesUnknown |
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.
Subscription includes TTS/EVI/Voice allowances; overage and managed external LLM usage add cost.
Realtime model tokens plus input transcription, tools and carrier/hosting; not GPT-Live session-minute billing.
Free plan exists; paid entry is not a complete phone-call bill.
Cached audio/text and image inputs have separate rates. Rate is not per-minute.
Incompatible product allowances are not collapsed into one all-in minute price.
Model scope fixed to GPT-Realtime-2, not all voice models.
First-month Creator promotion is separate from regular price; Enterprise custom.
Published Realtime token rates do not establish these account/contract terms. GPT-Live duration billing and unrelated fine-tuning discounts must not be imported.
Plan-scoped EVI allowance; does not include every third-party carrier/model charge.
Published Realtime token rates do not establish these account/contract terms. GPT-Live duration billing and unrelated fine-tuning discounts must not be imported.
TTS characters, EVI minutes and supplemental model usage remain separate.
Published Realtime token rates do not establish these account/contract terms. GPT-Live duration billing and unrelated fine-tuning discounts must not be imported.
Repeated context, cache behavior and turn count affect token charges.
Not yet researched against this buyer-critical field standard.
Not yet researched against this buyer-critical field standard.
Full bill requires measured model/token/cache/tool/carrier usage; conversation minutes alone are insufficient.
Full bill requires measured model/token/cache/tool/carrier usage; conversation minutes alone are insufficient.
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.
Hume AI
VoiceAgent.best recommends evaluating migration options rather than starting a new long-term TTS or EVI API deployment. This is our editorial judgment; replacement compatibility has not been established.
$3/month Starter; included EVI minutes and overage depend on plan · V3.3 evidence review · Starter subscription reference; EVI 40 minutes; external LLM/telephony extra
Excluded / confirm: Complete cost cannot be established from this reference. Selected external LLM, carrier, token/character consumption and overages prevent a complete cost ceiling from monthly minutes alone. · Hume-managed external LLM usage extra; BYO key/custom model paid outside Hume; Twilio separate
Subscription includes TTS/EVI/Voice allowances; overage and managed external LLM usage add cost.
OpenAI Realtime API
A token rate cannot be compared directly with a bundled call-minute price.
GPT-Realtime-2 audio input $32/M, audio output $64/M; text input $4/M, output $24/M · V3.3 evidence review · GPT-Realtime-2 input audio tokens only; output/audio/text/cache have different rates; not 2.1 rate evidence
Excluded / confirm: Complete cost cannot be established from this reference. Full bill requires measured model/token/cache/tool/carrier usage; conversation minutes alone are insufficient. · Input transcription, tool/backend calls, carrier and application infrastructure
Realtime model tokens plus input transcription, tools and carrier/hosting; not GPT-Live session-minute billing.
The evidence overlap.
Both records have documented values for Product type, Technical setup, Pricing model, Published numeric pricing, Realtime / streaming audio, OpenAI models, Interruption controls, Official product documentation, Checked within 30 days, Retained price snapshot. 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.
Review Hume API sunset & migration guidance →