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.
Raw data and contributions are also maintained on GitHub: awesome-voice-ai-latency.
source & further reading
dev.to — original article
Google WeatherNext 3 Delivers Finer Global AI Forecasts for Weather-Sensitive Operations
Google Search Agents Signal a Shift From Queries to Background Tasks and Transactions
Why I Built Lexis - A Free, Local-First AI Productivity Suite