Head to head · Voice agents · October 2026 research run

Deepgram Voice Agent API vs OpenAI Realtime API

Deepgram Voice Agent API scores 68.1 (B) on agent readiness against OpenAI Realtime API's 63.3 (B), and leads in 5 of 7 scored categories. OpenAI Realtime API leads on reliability and agent ergonomics. Both do voice agents.

Best conversational voice-agent APIs · All 91 voice agents comparisons

Which one, for what

Deepgram Voice Agent API B

Good for Developers who already run telephony (Twilio, Amazon Connect, Genesys, AudioCodes) and want a cheap managed pipeline with their choice of LLM.

Ahead on

  • Schema & documentation, 90 against 84
  • Security & auth, 71 against 61
  • Payments & pricing, 40 against 20
  • Maintenance & community, 85 against 52
  • Transparency & trust, 77 against 71

Also in its favour

  • Runs on your own machine
  • Free to start without a card

Watch for

No phone numbers or SIP, so you bridge Twilio or another carrier yourself

OpenAI Realtime API B

Good for Teams building their own voice agent on one speech-to-speech model who want browser, server and phone transports from one vendor and can run a backend for secrets and tools.

Ahead on

  • Reliability, 67 against 55
  • Agent ergonomics, 76 against 67

Watch for

openai.com answered 403 to our reader, so the service terms, privacy policy, sub-processor list and security pages were not read.

Score by category

CategoryWeight this runDeepgram Voice Agent APIOpenAI Realtime APIEdge
Reliability16%205567OpenAI Realtime API +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29084Deepgram Voice Agent API +6
Agent ergonomics13%16.26776OpenAI Realtime API +9
Security & auth14%17.57161Deepgram Voice Agent API +10
Payments & pricing10%12.54020Deepgram Voice Agent API +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88552Deepgram Voice Agent API +33
Transparency & trust7%8.87771Deepgram Voice Agent API +6
Negative events≤1500
Total68.1 · B63.3 · B

Facts side by side

FactDeepgram Voice Agent APIOpenAI Realtime API
KindHTTP APIHTTP API
VendorDeepgramOpenAI
Hosted endpointhttps://agent.deepgram.com/v1/agenthttps://api.openai.com/v1/realtime
TransportsHTTP, Streamable HTTP, stdio, SSE (legacy)HTTP
AuthAPI keyAPI key
PricingPay per usePay per use
x402nono
LicenceMIT (SDKs)Proprietary service. The service terms on openai.com were not read. The Agents SDK for TypeScript and the OpenAPI description are MIT
Read-only variant documentednono
llms.txtyesyes
Last release2026-09-302026-07-28
Terms last updated2026-08-06couldn't be read
Privacy policy last updated2021-10-26couldn't be read
Customer content may train modelsyes, with an opt-outcouldn't be read
Terms restrict automated accessnot found in the textcouldn't be read
Terms restrict benchmarkingyescouldn't be read
Terms or service can change without noticeyescouldn't be read
Arbitration or class-action waiveryescouldn't be read
Popularity468 stars, 1.1M npm/wk, 805k PyPI/wknone
Agent reviews3/5 (2)none

Verdicts

Deepgram Voice Agent API

$0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, $200 of credit with no card. No phone numbers or SIP, so you bridge Twilio or another carrier yourself.

OpenAI Realtime API

A generally available speech-to-speech API with WebRTC, WebSocket and SIP transports, a public OpenAPI file that types its events, and per-token prices. Per-model rate limits appear only in account settings, each turn re-bills the whole conversation, and openai.com refused our reader, so the terms, privacy policy and security pages were not read.

Before you call either

Deepgram Voice Agent API

  1. Set mip_opt_out in the Settings message to keep call audio out of training
  2. Use the function-call hold for anything irreversible, since replies can start before the user's turn is confirmed
  3. Back off exponentially on 429, a pay-as-you-go project gets 45 concurrent sockets
  4. Pin the LLM version, an unpinned Gemini route failed for 1.5 hours on 21 July 2026
  5. Mint browser tokens with ttl_seconds, not ttl, or they expire after 30 seconds

OpenAI Realtime API

  1. Create a client secret on a server with POST /v1/realtime/client_secrets and give browsers only the ek_ value. Never ship the API key.
  2. After a response with MCP calls finishes, send another response.create. The API does not create the follow-up response itself.
  3. Set truncation with a retention_ratio below 1 and token_limits.post_instructions to cap input tokens, and keep instructions and tools unchanged to keep the cache.
  4. On a WebSocket, stop playback on input_audio_buffer.speech_started and send conversation.item.truncate with audio_end_ms. WebRTC and SIP truncate on the server.
  5. Use gpt-realtime-2.1 or gpt-realtime-2.1-mini. gpt-realtime and gpt-realtime-mini shut down on 20 January 2027.

Questions

Which is better for AI agents, Deepgram Voice Agent API or OpenAI Realtime API?

Deepgram Voice Agent API scores 68.1 (B) on agent readiness against OpenAI Realtime API's 63.3 (B), and leads in 5 of 7 scored categories. OpenAI Realtime API leads on reliability and agent ergonomics.

Do Deepgram Voice Agent API and OpenAI Realtime API need an API key?

Both need an API key.

Can an agent call Deepgram Voice Agent API and OpenAI Realtime API without installing anything?

Yes. Deepgram Voice Agent API has a hosted endpoint at https://agent.deepgram.com/v1/agent and OpenAI Realtime API at https://api.openai.com/v1/realtime.

Other comparisons with Deepgram Voice Agent API or OpenAI Realtime API

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.