Text-to-Speech · Multilingual

Swahili

Language

Request a new language

Tell us which language you want added to this benchmark.

Benchmarks

X
Y
0.400.60200ms400ms600ms800ms1.00sRobustness higher is betterTime to first audio lower is betterSoniox tts-rt-v2ElevenLabs eleven_v4_turboElevenLabs eleven_v4Gemini 3.8-flash-ttsspeko.ai/benchmarks

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 Swahili voices.

InworldInworldtts-287ms · 99ms
ElevenLabseleven_v4_turbo240ms · 392ms
Sonioxtts-rt-v2317ms · 363ms
ElevenLabseleven_v4594ms · 807ms
GeminiGemini3.8-flash-tts973ms · 1.04s
0ms300ms600ms900ms

p50 p90

Robustness

higher is better

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

0.73
Azure0.63
Google Chirp 3 HD0.55
0.50
Gemini0.50
0.45
Gemini0.25
Gemini0.20
0.00
0.00
0.00
Speechify0.00
0.00
0.000.250.500.751.00

Cost

lower is better

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