Text-to-Speech · Multilingual

Hindi

Language

Request a new language

Tell us which language you want added to this benchmark.

Benchmarks

X
Y
200ms400ms600ms800ms150016001700Time to first audio lower is betterNaturalness higher is betterCartesia sonic-3.5Gemini 3.1-flash-tts-previewMiniMax speech-2.8-hdElevenLabs eleven_v3_conversationalMaya 2 Nativespeko.ai/benchmarks

Naturalness

higher is better

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

field averagetied with bestSpeechifySpeechifysimba-multilingual1310AzureAzureAI Speech (native)1412Google ChirpGoogle Chirp3-hd1468Maya2 Native1478ElevenLabseleven_v3_conversational1490MiniMaxMiniMaxspeech-2.8-hd1522GeminiGemini3.1-flash-tts-preview1563SpeechifySpeechifysimba-3.51680Cartesiasonic-3.51736
100012001400160018002000

Time to first audio

lower is better

The pause the caller hears before the agent starts speaking. Figures are the English measurement — Hindi has no sweep of its own yet.

Maya2 Native100ms · 114ms
Cartesiasonic-3.5108ms · 234ms
xAI Groktts251ms · 291ms
ElevenLabseleven_v3_conversational255ms · 298ms
MiniMaxMiniMaxspeech-2.8-hd329ms · 429ms
ElevenLabseleven_v3474ms · 622ms
GeminiGemini3.1-flash-tts-preview810ms · 987ms
0ms300ms600ms900ms

p50 p90

Robustness

higher is better

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

Speechify0.86
0.75
0.75
0.73
0.48
Gemini0.43
MiniMax0.28
Google Chirp0.25
0.18
Speechify0.03
0.000.250.500.751.00

Cost

lower is better

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