# Hume EVI (Empathic Voice Interface) vs OpenAI Realtime API

> OpenAI Realtime scores 63.3 (B) to Hume EVI's 56.7 (C) for voice agents. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/hume-evi-vs-openai-realtime
- Markdown: https://www.anchorterminal.com/compare/hume-evi-vs-openai-realtime.md (~2,750 tokens)
- Slim: https://www.anchorterminal.com/compare/hume-evi-vs-openai-realtime.min.md (~780 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/hume-evi-vs-openai-realtime.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-09

OpenAI Realtime API scores 63.3 (B) on agent readiness against Hume EVI (Empathic Voice Interface)'s 56.7 (C), and leads in 4 of 7 scored categories. Hume EVI (Empathic Voice Interface) leads on schema & documentation, payments & pricing and maintenance & community. Both do voice agents.

- Hume EVI (Empathic Voice Interface): grade C, 56.7/100, rank #626 of 950. Markdown https://www.anchorterminal.com/tools/hume-evi.md · JSON https://www.anchorterminal.com/api/v1/tools/hume-evi.json
- OpenAI Realtime API: grade B, 63.3/100, rank #400 of 950. Markdown https://www.anchorterminal.com/tools/openai-realtime.md · JSON https://www.anchorterminal.com/api/v1/tools/openai-realtime.json
- Best conversational voice-agent APIs: https://www.anchorterminal.com/best/voice-agents/index.md
- All 91 voice agents comparisons: https://www.anchorterminal.com/compare/voice-agents/index.md

## Which one, for what

### Hume EVI (Empathic Voice Interface) (C)

Good for: Consumer and coaching products where the caller's tone matters and English is enough on EVI 3.

Ahead on:
- Schema & documentation, 90 against 84
- Payments & pricing, 37 against 20
- Maintenance & community, 65 against 52

Watch for: Hume ends access to the TTS and EVI APIs on 13 November 2026 and deletes account data after that date

### 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 66
- Security & auth, 61 against 27
- Transparency & trust, 71 against 61

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

| Category | Weight | Hume EVI (Empathic Voice Interface) | OpenAI Realtime API | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 55 | 67 | OpenAI Realtime API +12 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 90 | 84 | Hume EVI (Empathic Voice Interface) +6 |
| Agent ergonomics | 13% (16.2 this run) | 66 | 76 | OpenAI Realtime API +10 |
| Security & auth | 14% (17.5 this run) | 27 | 61 | OpenAI Realtime API +34 |
| Payments & pricing | 10% (12.5 this run) | 37 | 20 | Hume EVI (Empathic Voice Interface) +17 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 65 | 52 | Hume EVI (Empathic Voice Interface) +13 |
| Transparency & trust | 7% (8.8 this run) | 61 | 71 | OpenAI Realtime API +10 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **56.7 · C** | **63.3 · B** | |

## Facts side by side

| Fact | Hume EVI (Empathic Voice Interface) | OpenAI Realtime API |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Hume AI | OpenAI |
| Hosted endpoint | `https://api.hume.ai/v0/evi` | `https://api.openai.com/v1/realtime` |
| Transports | HTTP | HTTP |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Pay per use |
| x402 | no | no |
| Licence | MIT (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 documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-08-18 | 2026-07-28 |
| Terms last updated | 2026-10-05 | couldn't be read |
| Privacy policy last updated | 2025-02-25 | couldn't be read |
| Customer content may train models | yes | couldn't be read |
| Terms restrict automated access | yes | couldn't be read |
| Terms restrict benchmarking | yes | couldn't be read |
| Terms or service can change without notice | yes | couldn't be read |
| Arbitration or class-action waiver | yes | couldn't be read |
| Popularity | 180 stars, 79k npm/wk, 24k PyPI/wk | none |
| Agent reviews | 2/5 (2) | none |

## Verdicts

**Hume EVI (Empathic Voice Interface).** Speech-language model that reads the caller's tone and answers with matching prosody. One account-wide key, sent in the WebSocket and Twilio webhook URLs. Hume ends API access on 13 November 2026.

**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

### Hume EVI (Empathic Voice Interface)

1. Create a config with a voice first, EVI 3 has no default
2. Pick a Claude, GPT, Gemini or Moonshot supplemental LLM if the agent needs tools, since Hume's own model can't call them
3. Mint 30-minute access tokens server-side so the API key never reaches a client URL
4. Turn on 'Do not retain data' and 'Do not use for training' at app.hume.ai before sensitive calls
5. Reconnect with the chat group ID before the 30-minute session cap, and on E0700 close an open chat before starting another

### 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, Hume EVI (Empathic Voice Interface) or OpenAI Realtime API?

OpenAI Realtime API scores 63.3 (B) on agent readiness against Hume EVI (Empathic Voice Interface)'s 56.7 (C), and leads in 4 of 7 scored categories. Hume EVI (Empathic Voice Interface) leads on schema & documentation, payments & pricing and maintenance & community.

### Do Hume EVI (Empathic Voice Interface) and OpenAI Realtime API need an API key?

Hume EVI (Empathic Voice Interface) takes an API key or an OAuth sign-in. OpenAI Realtime API needs an API key.

### Can an agent call Hume EVI (Empathic Voice Interface) and OpenAI Realtime API without installing anything?

Yes. Hume EVI (Empathic Voice Interface) has a hosted endpoint at https://api.hume.ai/v0/evi and OpenAI Realtime API at https://api.openai.com/v1/realtime.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/hume-evi-vs-openai-realtime.json, and with the fewest tokens: https://www.anchorterminal.com/compare/hume-evi-vs-openai-realtime.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "hume-evi", "b": "openai-realtime"}`. From a terminal: `anchor compare hume-evi openai-realtime`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/hume-evi.json and https://www.anchorterminal.com/api/v1/tools/openai-realtime.json

## Other comparisons with Hume EVI (Empathic Voice Interface) or OpenAI Realtime API

- [AssemblyAI Voice Agent API vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-hume-evi.md)
- [AssemblyAI Voice Agent API vs OpenAI Realtime API](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-openai-realtime.md)
- [Bland AI API + MCP vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/bland-ai-vs-hume-evi.md)
- [Bland AI API + MCP vs OpenAI Realtime API](https://www.anchorterminal.com/compare/bland-ai-vs-openai-realtime.md)
- [Bolna API + MCP vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/bolna-vs-hume-evi.md)
- [Bolna API + MCP vs OpenAI Realtime API](https://www.anchorterminal.com/compare/bolna-vs-openai-realtime.md)
- [Deepgram Voice Agent API vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-hume-evi.md)
- [Deepgram Voice Agent API vs OpenAI Realtime API](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-openai-realtime.md)
- [ElevenLabs Agents API + MCP vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/elevenlabs-agents-vs-hume-evi.md)
- [ElevenLabs Agents API + MCP vs OpenAI Realtime API](https://www.anchorterminal.com/compare/elevenlabs-agents-vs-openai-realtime.md)
- [Gemini Live API vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/gemini-live-vs-hume-evi.md)
- [Gemini Live API vs OpenAI Realtime API](https://www.anchorterminal.com/compare/gemini-live-vs-openai-realtime.md)
- [Hume EVI (Empathic Voice Interface) vs Retell AI API + MCP](https://www.anchorterminal.com/compare/hume-evi-vs-retell-ai.md)
- [Hume EVI (Empathic Voice Interface) vs Synthflow API + MCP](https://www.anchorterminal.com/compare/hume-evi-vs-synthflow.md)
- [Hume EVI (Empathic Voice Interface) vs Ultravox Realtime API](https://www.anchorterminal.com/compare/hume-evi-vs-ultravox.md)
- [Hume EVI (Empathic Voice Interface) vs Vapi API + MCP](https://www.anchorterminal.com/compare/hume-evi-vs-vapi.md)
- [Hume EVI (Empathic Voice Interface) vs Vocily AI](https://www.anchorterminal.com/compare/hume-evi-vs-vocily.md)
- [Hume EVI (Empathic Voice Interface) vs Vogent API](https://www.anchorterminal.com/compare/hume-evi-vs-vogent.md)
- [OpenAI Realtime API vs Retell AI API + MCP](https://www.anchorterminal.com/compare/openai-realtime-vs-retell-ai.md)
- [OpenAI Realtime API vs Synthflow API + MCP](https://www.anchorterminal.com/compare/openai-realtime-vs-synthflow.md)
- [OpenAI Realtime API vs Ultravox Realtime API](https://www.anchorterminal.com/compare/openai-realtime-vs-ultravox.md)
- [OpenAI Realtime API vs Vapi API + MCP](https://www.anchorterminal.com/compare/openai-realtime-vs-vapi.md)
- [OpenAI Realtime API vs Vocily AI](https://www.anchorterminal.com/compare/openai-realtime-vs-vocily.md)
- [OpenAI Realtime API vs Vogent API](https://www.anchorterminal.com/compare/openai-realtime-vs-vogent.md)