Urgent.News

What's breaking now, across thousands of outlets.

More in AI

Benchmarking Real-Time Voice AI APIs: Cartesia vs Deepgram vs ElevenLabs (2026)

When building conversational agents or real-time voice applications, latency is the defining metric. If Time-to-First-Byte (TTFB) exceeds 200ms, natural turn-taking breaks down and conversational interruption becomes clunky.

  • Cartesia Sonic-3 has lowest latency at 85ms, ideal for real-time applications
  • Deepgram Aura-2 is most cost-effective at $15 per 1 million characters
  • ElevenLabs Flash v2.5 excels in voice realism with 135ms latency

More from Thursday 3 September →