CekuraBench

Grok TTSvsMAI-Voice-2.1-Flash

Grok TTSMAI-Voice-2.1-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
  • Grok TTS358 ms · 87.4%
  • MAI-Voice-2.1-Flash289 ms · 78.3%

Grok TTS is better on streaming latency, stopping and accuracy. MAI-Voice-2.1-Flash is better on non-streaming latency and naturalness.

Last updated Methodology by Dileep Chagam

Which is better at what

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

MeasureGrok TTSMAI-Voice-2.1-Flash
  • Non-streaming latency (median)MAI-Voice-2.1-Flash is better358 ms289 ms
  • Streaming latency (median)Grok TTS is better157 msCan't stream
  • Extra audio after a stopGrok TTS is better0 msNo stop message
  • Hard parts read rightGrok TTS is better87.4%78.3%
  • Naturalness (1 to 5)MAI-Voice-2.1-Flash is better4.174.32
  • Price per 1M charactersLevel$15.00$15.00
Hard parts read rightGrok TTSMAI-Voice-2.1-Flash
  • Numbers and shorthand7 a.m. · 20% · 36°F · approx.82%79%
  • Codes and addressesSAVE20 · help@north-clinic.org · 1-800-555-019986%67%
  • Read from contextSt. Mary's on Main St. · Dr. Okafor100%75%
  • Medical termslevothyroxine · gastroenterology99%92%

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

MeasureGrok TTSMAI-Voice-2.1-Flash
  • Non-streaming latency (median)18 of 2612 of 26
  • Streaming latency (median)7 of 18n/a
  • Extra audio after a stop1 of 6n/a
  • Hard parts read right8 of 2618 of 26
  • Naturalness (1 to 5)25 of 2622 of 26
  • Price per 1M characters2 of 252 of 25

Related comparisons

Grok TTS vs MAI-Voice-2.1-Flash FAQ

  • MAI-Voice-2.1-Flash. Grok TTS: 358 ms. MAI-Voice-2.1-Flash: 289 ms.

  • Grok TTS. Grok TTS: 157 ms. MAI-Voice-2.1-Flash: Can't stream.

  • Grok TTS. Grok TTS: 0 ms. MAI-Voice-2.1-Flash: No stop message.

  • Grok TTS. Grok TTS: 87.4%. MAI-Voice-2.1-Flash: 78.3%.

  • They are level. Grok TTS: $15.00. MAI-Voice-2.1-Flash: $15.00.