Deepgram FluxvsInworld TTS-2

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 Flux194 ms · 77.4%
  • Inworld TTS-2126 ms · 93.4%

Deepgram Flux is better on stopping. Inworld TTS-2 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.

MeasureDeepgram FluxInworld TTS-2
  • Non-streaming latency (median)Inworld TTS-2 is better194 ms126 ms
  • Streaming latency (median)Inworld TTS-2 is better154 ms127 ms
  • Extra audio after a stopDeepgram Flux is better80 msNo stop message
  • Hard parts read rightInworld TTS-2 is better77.4%93.4%
  • Naturalness (1 to 5)Inworld TTS-2 is better4.164.52
  • Price per 1M charactersInworld TTS-2 is better$45.00$25.00
Hard parts read rightDeepgram FluxInworld TTS-2
  • Numbers and shorthand7 a.m. · 20% · 36°F · approx.72%93%
  • Codes and addressesSAVE20 · help@north-clinic.org · 1-800-555-019981%86%
  • Read from contextSt. Mary's on Main St. · Dr. Okafor69%100%
  • Medical termslevothyroxine · gastroenterology97%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

MeasureDeepgram FluxInworld TTS-2
  • Non-streaming latency (median)6 of 263 of 26
  • Streaming latency (median)6 of 185 of 18
  • Extra audio after a stop4 of 6n/a
  • Hard parts read right19 of 261 of 26
  • Naturalness (1 to 5)26 of 262 of 26
  • Price per 1M characters21 of 2510 of 25

Deepgram Flux vs Inworld TTS-2 FAQ

  • Inworld TTS-2. Deepgram Flux: 194 ms. Inworld TTS-2: 126 ms.

  • Inworld TTS-2. Deepgram Flux: 154 ms. Inworld TTS-2: 127 ms.

  • Deepgram Flux. Deepgram Flux: 80 ms. Inworld TTS-2: No stop message.

  • Inworld TTS-2. Deepgram Flux: 77.4%. Inworld TTS-2: 93.4%.

  • Inworld TTS-2. Deepgram Flux: $45.00. Inworld TTS-2: $25.00.