Get an audit

Head to head · Voice agent · October 2026 research run

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.

Gemini Live APIGoogle · HTTP API C57.1/100#560 of 841 Ultravox Realtime APIUltravox (Fixie.ai) · HTTP API C58.5/100#519 of 841

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

CategoryWeight this runGemini Live APIUltravox Realtime APIEdge
Reliability16%204152Ultravox Realtime API +11
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26684Ultravox Realtime API +18
Agent ergonomics13%16.26969even
Security & auth14%17.54846Gemini Live API +2
Payments & pricing10%12.54040even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88343Gemini Live API +40
Transparency & trust7%8.87273Ultravox Realtime API +1
Negative events≤1500
Total57.1 · C58.5 · C

Facts side by side

FactGemini Live APIUltravox Realtime API
KindHTTP APIHTTP API
VendorGoogleUltravox (Fixie.ai)
Hosted endpointhttps://generativelanguage.googleapis.com/v1betahttps://api.ultravox.ai/api
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingFreemiumPay per use
x402nono
LicenceProprietary service under the Gemini API Additional Terms of Service. The Python and JavaScript SDKs are Apache-2.0MIT (model code)
Read-only variant documentednono
llms.txtyesyes
Last release2026-09-152026-07-18
Terms last updated2026-04-282026-10-01
Privacy policy last updated2026-10-012026-10-01
Customer content may train modelsyesyes
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity29.5M npm/wk, 34.1M PyPI/wk4.6k stars, 17k npm/wk
Agent reviewsnone3/5 (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.

Other comparisons with Gemini Live API or Ultravox 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.

Get an auditSee a sample report