PROVIDERLAST 30 DAYS

Cloudflare voice AI models and benchmarks

Cloudflare lists 1 TTS model in Coval. Its fastest dated TTS result is Aura 2 En at mean 515 ms time to first audio (29th of 32) among TTS systems, with 1.9% WER. Results cover the last 30 days. Last measured .

Coval measures voice models created or hosted by Cloudflare.

Measured models
1
TTS

Overview

Every model below is measured daily on the same fixed inputs and ranked against the full field, never blended into a company score.

Model lineup

Text-to-Speech
serves Aura 2 En

Ranked on Time to First Audio against 32 measured models.

Time to First Audioms · lower is better · Cloudflare models markedEvery measured TTS model on Time to First Audio, with Cloudflare's models highlighted.
  1. #1vui40 ms
  2. #2Default63 ms
  3. #3PhantomZ 4.064 ms
  4. #4TTS Flash 268 ms
  5. #6Simba 3.2101 ms
  6. #7Qwen3 TTS 1.7b105 ms
  7. #29Aura 2 En515 ms
leaders plus Cloudflare models · 24 other models in the full table
Word Error Rate% · lower is better · Cloudflare models markedEvery measured TTS model on Word Error Rate, with Cloudflare's models highlighted.
leaders plus Cloudflare models · 24 other models in the full table
Benchmarked models with their Time to First Audio over the last 30 days.
ModelHostTTFARank
Aura 2 EnCloudflare515 ms29th of 32

How fast are Cloudflare's TTS models?

Aura 2 En measures mean 515 ms time to first audio (29th of 32) among TTS systems. Last measured 2026-11-21.

How accurate are Cloudflare's TTS models?

Aura 2 En measures 1.9% word error rate (25th of 32) among TTS systems. Last measured 2026-11-21.

Which Cloudflare model is fastest?

Its fastest dated TTS result is Aura 2 En at mean 515 ms time to first audio (29th of 32) among TTS systems, with 1.9% WER. Last measured 2026-11-21.

Same datasets, prompts and metric definitions for every model, measured by Coval’s open-source runner. Full methodology on the overview.

Evaluate your own voice agent

Use Coval to test your production configuration, prompts and calls—not only the public benchmark endpoints.

Book a Demo