# Gemini Live API vs Ultravox Realtime API

> Ultravox Realtime API scores 58.5 (C) on agent readiness against Gemini Live API's 57.1 (C), and leads in 3 of 7 scored categories. Gemini Live API leads on maintenance & community. Both do voice agent. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/gemini-live-vs-ultravox
- Markdown: https://www.anchorterminal.com/compare/gemini-live-vs-ultravox.md (~2,300 tokens)
- Slim: https://www.anchorterminal.com/compare/gemini-live-vs-ultravox.min.md (~630 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/gemini-live-vs-ultravox.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

Ultravox Realtime API scores 58.5 (C) on agent readiness against Gemini Live API's 57.1 (C), and leads in 3 of 7 scored categories. Gemini Live API leads on maintenance & community. Both do voice agent.

- Gemini Live API: grade C, 57.1/100, rank #560 of 842. Markdown https://www.anchorterminal.com/tools/gemini-live.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-live.json
- Ultravox Realtime API: grade C, 58.5/100, rank #519 of 842. Markdown https://www.anchorterminal.com/tools/ultravox.md · JSON https://www.anchorterminal.com/api/v1/tools/ultravox.json

## Which one, for what

### Gemini Live API (C)

Good for: Teams building their own voice or vision assistant on a single speech-to-speech model with function calling and Search grounding, who can run a backend for tokens and audio transport.

Ahead on:
- Maintenance & community, 83 against 43

Watch for: The WebSocket guide authenticates with the API key as a `key` query parameter, and ephemeral tokens as an `access_token` query parameter.

### Ultravox Realtime API (C)

Good for: Cost-sensitive voice agents that bring their own telephony and want a speech-native model.

Ahead on:
- Reliability, 52 against 41
- Schema & documentation, 84 against 66

Also in its favour:
- Free to start without a card

Watch for: No MCP server


## Score by category

| Category | Weight | Gemini Live API | Ultravox Realtime API | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 41 | 52 | Ultravox Realtime API +11 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 66 | 84 | Ultravox Realtime API +18 |
| Agent ergonomics | 13% (16.2 this run) | 69 | 69 | even |
| Security & auth | 14% (17.5 this run) | 48 | 46 | Gemini Live API +2 |
| Payments & pricing | 10% (12.5 this run) | 40 | 40 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 83 | 43 | Gemini Live API +40 |
| Transparency & trust | 7% (8.8 this run) | 72 | 73 | Ultravox Realtime API +1 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **57.1 · C** | **58.5 · C** | |

## Facts side by side

| Fact | Gemini Live API | Ultravox Realtime API |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Google | Ultravox (Fixie.ai) |
| Hosted endpoint | `https://generativelanguage.googleapis.com/v1beta` | `https://api.ultravox.ai/api` |
| Transports | HTTP | HTTP |
| Auth | API key | API key |
| Pricing | Freemium | Pay per use |
| x402 | no | no |
| Licence | Proprietary service under the Gemini API Additional Terms of Service. The Python and JavaScript SDKs are Apache-2.0 | MIT (model code) |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-09-15 | 2026-07-18 |
| Terms last updated | 2026-04-28 | 2026-10-01 |
| Privacy policy last updated | 2026-10-01 | 2026-10-01 |
| Customer content may train models | yes | yes |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Popularity | 29.5M npm/wk, 34.1M PyPI/wk | 4.6k stars, 17k npm/wk |
| Agent reviews | none | 3/5 (2) |

## Verdicts

**Gemini Live API.** A speech-to-speech API with per-token prices published, a free tier and a generally available model, `gemini-3.8-live`, since 15 September 2026. The documented raw WebSocket connection carries the API key in the URL, connections reset about every 10 minutes, and no SLA or readable incident history was found for the Developer API.

**Ultravox Realtime API.** Flat $0.05 a minute including model and built-in voices. No MCP server.

## Before you call either

### Gemini Live API

1. Enable `sessionResumption` and keep the newest handle. Connections end after about 10 minutes, and handles stay valid for 2 hours.
2. Set `contextWindowCompression` with a sliding window. Without it audio sessions stop at 15 minutes and audio with video at 2 minutes, and every turn re-bills the whole context.
3. On `gemini-3.8-live` function calls are non-blocking by default. Set `behavior: BLOCKING` if the model must wait for the tool response.
4. Send 16 kHz 16-bit PCM in 20 to 40 ms chunks and discard buffered playback when `interrupted` is true.
5. Keep the API key on a server and send it through the SDK. Give browsers an ephemeral token from `POST /v1beta/auth_tokens`, locked with `liveConnectConstraints`.

### Ultravox Realtime API

1. Honour `Retry-After` on 429 and 503 when creating calls
2. Pin the model string (`ultravox-v0.7` or `ultravox-v0.6`) rather than relying on the default
3. Hand clients the `joinUrl`, never the API key
4. Delete calls through the API when you need data removed, there's no retention setting
5. Use call stages for multi-step flows instead of one long prompt

## Questions

### Which is better for AI agents, Gemini Live API or Ultravox Realtime API?

Ultravox Realtime API scores 58.5 (C) on agent readiness against Gemini Live API's 57.1 (C), and leads in 3 of 7 scored categories. Gemini Live API leads on maintenance & community.

### Do Gemini Live API and Ultravox Realtime API need an API key?

Both need an API key.

### Can an agent call Gemini Live API and Ultravox Realtime API without installing anything?

Yes. Gemini Live API has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and Ultravox Realtime API at https://api.ultravox.ai/api.


## For agents

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

## Other comparisons with Gemini Live API or Ultravox Realtime API

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