Thai

1500 is this language's own field — not comparable across languages.

field averagetied with bestOpenAIgpt-4o-mini-tts1084Inworldtts-21202AzureAI Speech (native)1280Google Chirp 3 HD1442Paxatts-flash-v11467Sonioxtts-rt-v21591ElevenLabseleven_v31605Cartesiasonic-3.51688MiniMaxspeech-2.6-hd1699xAI Groktts1719Gemini3.1-flash-tts-preview1722

80010001200140016001800

The pause the caller hears before the agent starts speaking. Measured from US East straight to each vendor, on the study's Thai voices.

AzureAI Speech (native)19ms · 62ms

Paxatts-flash-v152ms · 72ms

Speechifysimba-3.573ms · 277ms

Inworldtts-294ms · 101ms

Cartesiasonic-3.5176ms · 342ms

xAI Groktts283ms · 310ms

OpenAIgpt-4o-mini-tts459ms · 741ms

Gemini3.1-flash-tts-preview541ms · 616ms

MiniMaxspeech-2.6-hd2.00s · 2.44s

0ms600ms1.20s1.80s

p50 p90

Whether the voice says the right words for a number, date, currency amount or operator.

Gemini3.1-flash-tts-preview1.00

Paxatts-flash-v11.00

xAI Groktts1.00

Sonioxtts-rt-v21.00

AzureAI Speech (native)0.85

Google Chirp 3 HD0.85

Speechifysimba-3.50.75

Cartesiasonic-3.50.75

MiniMaxspeech-2.6-hd0.60

OpenAIgpt-4o-mini-tts0.25

ElevenLabseleven_v30.00

Inworldtts-20.00

0.000.250.500.751.00

$ per 1M characters · vendor list price, the same in every language

$0$25$50$75$100

$10

$13

$15

$20

$20

$25

$33

$50

$100

Paxatts-flash-v1Sonioxtts-rt-v2xAI GrokttsOpenAIgpt-4o-mini-ttsSpeechifysimba-3.5Inworldtts-2Gemini3.1-flash-tts-previewCartesiasonic-3.5MiniMaxspeech-2.6-hd