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

A developer benchmarked real-time voice AI APIs from Cartesia, Deepgram, ElevenLabs, PlayHT, and OpenAI, measuring median latency and pricing across 1,000 WebSocket requests. Cartesia's Sonic-3 achieved the fastest time-to-first-byte at 85ms, while Deepgram's Aura-2 offered the lowest bulk cost at $15 per 1M characters. The results highlight trade-offs between speed, cost, and voice realism for conversational agents.

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. We recently recorded and aggregated median latency and pricing metrics across the primary streaming Text-to-Speech APIs using WebSocket connections US-East endpoints, median across 1,000 requests . | Provider | Model | TTFB Latency | Pricing / 1M Chars | Real-Time Suitability | |---|---|---|---|---| Cartesia | Sonic-3 | 85ms | $20.00 | Excellent Fastest turn-taking | Deepgram | Aura-2 | 115ms | $15.00 | Very Good Lowest bulk cost | ElevenLabs | Flash v2.5 | 135ms | $25.00 | Best Voice Realism | PlayHT | PlayDialog | 180ms | $25.00 | Good | OpenAI | TTS-1 | 240ms | $15.00 | Slower Chunked HTTP | The full benchmark dataset, methodology, and continuous updates are documented at VoiceAIBench https://voiceaibench.com . Raw data and contributions are also maintained on GitHub: awesome-voice-ai-latency https://github.com/mrzitoun/awesome-voice-ai-latency/ .