CekuraBench

Deepgram Aura-2vsMAI-Voice-2.1-Flash

Deepgram Aura-2MAI-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
  • Deepgram Aura-2281 ms · 77.2%
  • MAI-Voice-2.1-Flash289 ms · 78.3%

Deepgram Aura-2 is better on non-streaming latency, streaming latency, stopping and naturalness. MAI-Voice-2.1-Flash is better on accuracy and price.

Last updated Methodology by Dileep Chagam

Which is better at what

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

MeasureDeepgram Aura-2MAI-Voice-2.1-Flash
  • Non-streaming latency (median)Deepgram Aura-2 is better281 ms289 ms
  • Streaming latency (median)Deepgram Aura-2 is better126 msCan't stream
  • Extra audio after a stopDeepgram Aura-2 is better40 msNo stop message
  • Hard parts read rightMAI-Voice-2.1-Flash is better77.2%78.3%
  • Naturalness (1 to 5)Deepgram Aura-2 is better4.434.32
  • Price per 1M charactersMAI-Voice-2.1-Flash is better$30.00$15.00
Hard parts read rightDeepgram Aura-2MAI-Voice-2.1-Flash
  • Numbers and shorthand7 a.m. · 20% · 36°F · approx.71%79%
  • Codes and addressesSAVE20 · help@north-clinic.org · 1-800-555-019987%67%
  • Read from contextSt. Mary's on Main St. · Dr. Okafor75%75%
  • Medical termslevothyroxine · gastroenterology86%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

MeasureDeepgram Aura-2MAI-Voice-2.1-Flash
  • Non-streaming latency (median)9 of 2612 of 26
  • Streaming latency (median)4 of 18n/a
  • Extra audio after a stop3 of 6n/a
  • Hard parts read right20 of 2618 of 26
  • Naturalness (1 to 5)8 of 2622 of 26
  • Price per 1M characters13 of 252 of 25

Related comparisons

Deepgram Aura-2 vs MAI-Voice-2.1-Flash FAQ

  • Deepgram Aura-2. Deepgram Aura-2: 281 ms. MAI-Voice-2.1-Flash: 289 ms.

  • Deepgram Aura-2. Deepgram Aura-2: 126 ms. MAI-Voice-2.1-Flash: Can't stream.

  • Deepgram Aura-2. Deepgram Aura-2: 40 ms. MAI-Voice-2.1-Flash: No stop message.

  • MAI-Voice-2.1-Flash. Deepgram Aura-2: 77.2%. MAI-Voice-2.1-Flash: 78.3%.

  • MAI-Voice-2.1-Flash. Deepgram Aura-2: $30.00. MAI-Voice-2.1-Flash: $15.00.