CekuraBench

ElevenLabs v4 TurbovsInworld TTS-2 Flash

ElevenLabs v4 TurboInworld TTS-2 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
  • ElevenLabs v4 Turbo176 ms · 79.9%
  • Inworld TTS-2 Flash46 ms · 93.2%

Inworld TTS-2 Flash is better on non-streaming latency, streaming latency, accuracy, naturalness and price.

Last updated Methodology by Dileep Chagam

Which is better at what

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

MeasureElevenLabs v4 TurboInworld TTS-2 Flash
  • Non-streaming latency (median)Inworld TTS-2 Flash is better176 ms46 ms
  • Streaming latency (median)Inworld TTS-2 Flash is better69 ms45 ms
  • Extra audio after a stopFinishes firstNo stop message
  • Hard parts read rightInworld TTS-2 Flash is better79.9%93.2%
  • Naturalness (1 to 5)Inworld TTS-2 Flash is better4.424.46
  • Price per 1M charactersInworld TTS-2 Flash is better$40.00$15.00
Hard parts read rightElevenLabs v4 TurboInworld TTS-2 Flash
  • Numbers and shorthand7 a.m. · 20% · 36°F · approx.71%93%
  • Codes and addressesSAVE20 · help@north-clinic.org · 1-800-555-019982%86%
  • Read from contextSt. Mary's on Main St. · Dr. Okafor88%98%
  • Medical termslevothyroxine · gastroenterology100%99%

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

MeasureElevenLabs v4 TurboInworld TTS-2 Flash
  • Non-streaming latency (median)4 of 261 of 26
  • Streaming latency (median)3 of 182 of 18
  • Extra audio after a stopn/an/a
  • Hard parts read right16 of 262 of 26
  • Naturalness (1 to 5)11 of 265 of 26
  • Price per 1M characters18 of 252 of 25

Related comparisons

ElevenLabs v4 Turbo vs Inworld TTS-2 Flash FAQ

  • Inworld TTS-2 Flash. ElevenLabs v4 Turbo: 176 ms. Inworld TTS-2 Flash: 46 ms.

  • Inworld TTS-2 Flash. ElevenLabs v4 Turbo: 69 ms. Inworld TTS-2 Flash: 45 ms.

  • Neither has a figure. ElevenLabs v4 Turbo: Finishes first. Inworld TTS-2 Flash: No stop message.

  • Inworld TTS-2 Flash. ElevenLabs v4 Turbo: 79.9%. Inworld TTS-2 Flash: 93.2%.

  • Inworld TTS-2 Flash. ElevenLabs v4 Turbo: $40.00. Inworld TTS-2 Flash: $15.00.