CekuraBench

GPT-4o mini TTSvsGemini 3.8 Flash

GPT-4o mini TTSGemini 3.8 Flash
Compare

Speed and accuracy

Left is faster. Higher reads more hard parts right.

Fast and accurate60%70%80%90%100%00.5s1s1.5s2sTime until the caller hears the voice
  • GPT-4o mini TTS688 ms · 82.7%
  • Gemini 3.8 Flash1.29 s · 87.7%

GPT-4o mini TTS is better on non-streaming latency and price. Gemini 3.8 Flash is better on accuracy and naturalness.

Last updated Methodology by Dileep Chagam

Which is better at what

Measure by measure, the same sentences, the same place.

MeasureGPT-4o mini TTSGemini 3.8 Flash
  • Non-streaming latency (median)GPT-4o mini TTS is better688 ms1.29 s
  • Streaming latency (median)Can't streamCan't stream
  • Extra audio after a stopNo stop messageNo stop message
  • Hard parts read rightGemini 3.8 Flash is better82.7%87.7%
  • Naturalness (1 to 5)Gemini 3.8 Flash is better4.434.46
  • Price per 1M charactersGPT-4o mini TTS is better$25.70$28.66
Hard parts read rightGPT-4o mini TTSGemini 3.8 Flash
  • Numbers and shorthand7 a.m. · 20% · 36°F · approx.78%84%
  • Codes and addressesSAVE20 · help@north-clinic.org · 1-800-555-019978%82%
  • Read from contextSt. Mary's on Main St. · Dr. Okafor96%98%
  • Medical termslevothyroxine · gastroenterology94%100%

An estimate: speech-to-text transcribers scored it, not people.

Hear both

The same sentence, read by each voice.

19 sentences, the same for both
  1. 01A greetingThanks for calling Cedar Valley Family Practice, this is Riley. How can I help you today?
  2. 02MoneyYour current balance is $1,347.09.
  3. 03A dateThe order was placed on 2026-03-14 and shipped two days later.
  4. 04Tracking codeThe tracking number is 1Z 7A4 X29 0341 8867.
  5. 05Email addressI have m.rivera88@example.org, is that still current?
  6. 06An Irish nameSiobhan Ó Briain called about the invoice.

How each ranks among all 26

MeasureGPT-4o mini TTSGemini 3.8 Flash
  • Non-streaming latency (median)21 of 2625 of 26
  • Streaming latency (median)n/an/a
  • Extra audio after a stopn/an/a
  • Hard parts read right12 of 266 of 26
  • Naturalness (1 to 5)7 of 266 of 26
  • Price per 1M characters11 of 2512 of 25

Related comparisons

GPT-4o mini TTS vs Gemini 3.8 Flash FAQ

  • GPT-4o mini TTS. GPT-4o mini TTS: 688 ms. Gemini 3.8 Flash: 1.29 s.

  • Neither has a figure. GPT-4o mini TTS: Can't stream. Gemini 3.8 Flash: Can't stream.

  • Neither has a figure. GPT-4o mini TTS: No stop message. Gemini 3.8 Flash: No stop message.

  • Gemini 3.8 Flash. GPT-4o mini TTS: 82.7%. Gemini 3.8 Flash: 87.7%.

  • GPT-4o mini TTS. GPT-4o mini TTS: $25.70. Gemini 3.8 Flash: $28.66.