Start building →OverviewMultilingualVoices

Text-to-Speech · Multilingual

Chinese (Mandarin)

Language

Request a new language

Tell us which language you want added to this benchmark.

Benchmarks

X
Y
200ms400ms600ms800ms1400150016001700Time to first audio lower is betterNaturalness higher is betterInworld tts-2ElevenLabs eleven_v3_conversationalGemini 3.1-flash-tts-previewCartesia sonic-3.5MiniMax speech-2.6-hdOpenAI gpt-4o-mini-ttsspeko.ai/benchmarks

Naturalness

higher is better

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

field averagetied with bestOpenAIgpt-4o-mini-tts1365MiniMaxMiniMaxspeech-2.6-hd1467AzureAzureAI Speech (native)1552Cartesiasonic-3.51564GeminiGemini3.1-flash-tts-preview1649ElevenLabseleven_v3_conversational1675InworldInworldtts-21688
1200140016001800

Time to first audio

lower is better

The pause the caller hears before the agent starts speaking.

InworldInworldtts-2121ms · 133ms
Cartesiasonic-3.5137ms · 193ms
MiniMaxMiniMaxspeech-2.6-hd340ms · 465ms
OpenAIgpt-4o-mini-tts602ms · 944ms
GeminiGemini3.1-flash-tts-preview634ms · 823ms
ElevenLabseleven_v3_conversational890ms · 1.13s
0ms300ms600ms900ms

p50 p90

Robustness

higher is better

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

Speechify1.00
Gemini0.75
0.75
MiniMax0.75
Inworld0.50
0.25
0.00
0.000.250.500.751.00

Cost

lower is better

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

$20
$20
$25
$33
$50
$50
$100
OpenAIgpt-4o-mini-ttsSpeechifySpeechifysimba-3.5InworldInworldtts-2GeminiGemini3.1-flash-tts-previewElevenLabseleven_v3_conversationalCartesiasonic-3.5MiniMaxMiniMaxspeech-2.6-hd