ElevenLabs publishes ~75ms for Flash v2.5, Deepgram 80ms for Flux TTS, Cartesia sub-90ms for Sonic, and Rime 37ms TTFA for Mist v3. We opened all four vendor pages on 10 September 2026 and traced every figure. None of them measures the same thing, and none of them is the number your callers will hear.
What this covers
- The four things that decide a TTS choice, before you look at a single number
- Which TTS publishes the lowest latency, and what each figure excludes
- How long does a real agent reply actually take? A worked example from Deepgram's own docs
- Why my dashboard shows 50ms and my caller still hears a pause
- How to measure TTS latency on my own stack in 20 minutes
This is a technical summary. The full guide — with the tables and worked examples — is on our site: *Fastest TTS for Voice Agents: Latency Compared*.
Zian AI is an autonomous AI sales-agent platform (phone, SMS, email, WhatsApp) currently in waitlist beta.
Top comments (0)