Text-to-Speech · Multilingual

Arabic

Language

Request a new language

Tell us which language you want added to this benchmark.

Benchmarks

X
Y
100ms200ms300ms1400150016001700Time to first audio lower is betterNaturalness higher is betterxAI Grok ttsCartesia sonic-3.5Hamsa defaultSoniox tts-rt-v2ElevenLabs eleven_v3_conversationalInworld tts-2Munsit faseeh-v1-previewspeko.ai/benchmarks

Naturalness

higher is better

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

field averagetied with bestMunsitMunsitfaseeh-v1-preview1401InworldInworldtts-21454SpeechifySpeechifysimba-3.51519ElevenLabseleven_v3_conversational1564Sonioxtts-rt-v21612HamsaHamsadefault1614Cartesiasonic-3.51644xAI Groktts1736
130014001500160017001800

Time to first audio

Region

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

InworldInworldtts-290ms · 98ms
Cartesiasonic-3.5152ms · 270ms
MunsitMunsitfaseeh-v1-preview200ms · 238ms
Sonioxtts-rt-v2210ms · 329ms
ElevenLabseleven_v3_conversational212ms · 240ms
HamsaHamsadefault322ms · 488ms
xAI Groktts336ms · 385ms
0ms150ms300ms

p50 p90

Robustness

higher is better

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

0.75
0.54
Gemini0.50
Speechify0.50
Munsit0.45
0.45
Hamsa0.40
Google Chirp0.32
0.29
MiniMax0.10
0.00
0.00
Inworld0.00
Speechify0.00
0.000.250.500.751.00

Cost

lower is better

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