Start with 45 free minutes of callsTry for free

Text-to-Speech · Multilingual

German

Language

Request a new language

Tell us which language you want added to this benchmark.

Benchmarks

X
Y

Naturalness

higher is better

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

field averagetied with bestDeepgramaura-2Try →1062GradiumTTSTry →1245SmallestSmallestlightning_v3.1Try →1254RimeRimearcanav3Try →1257OpenAIgpt-4o-mini-ttsTry →1497MiniMaxMiniMaxspeech-2.8-hdTry →1528QwenQwenqwen3-tts-flashTry →1573InworldInworldtts-2Try →1576SpeechifySpeechifysimba-3.5Try →1608Cartesiasonic-3.5Try →1665HumeHumeoctave-21687Sonioxtts-rt-v2Try →1700Sonioxtts-rt-v1Try →1717xAI GrokttsTry →1762ElevenLabseleven_v3_conversationalTry →1798
80010001200140016001800

Time to first audio

lower is better

The pause the caller hears before the agent starts speaking.

InworldInworldtts-2Try →118ms · 132ms
Deepgramaura-2Try →121ms · 128ms
Cartesiasonic-3.5Try →172ms · 239ms
SmallestSmallestlightning_v3.1Try →175ms · 213ms
RimeRimearcanav3Try →238ms · 245ms
xAI GrokttsTry →247ms · 276ms
ElevenLabseleven_v3_conversationalTry →261ms · 308ms
GradiumTTSTry →274ms · 284ms
MiniMaxMiniMaxspeech-2.8-hdTry →318ms · 350ms
Sonioxtts-rt-v1Try →404ms · 441ms
QwenQwenqwen3-tts-flashTry →411ms · 436ms
Sonioxtts-rt-v2Try →418ms · 458ms
HumeHumeoctave-2455ms · 646ms
ElevenLabseleven_v3Try →536ms · 590ms
OpenAIgpt-4o-mini-ttsTry →594ms · 1.03s
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.

GeminiGemini3.1-flash-tts-preview1.00
xAI GrokttsTry →1.00
SpeechifyTry →1.00
Try →0.97
Try →0.97
Try →0.97
Google Chirp0.95
Try →0.94
InworldTry →0.90
Try →0.75
Try →0.65
SpeechifyTry →0.55
MiniMaxTry →0.55
Try →0.40
QwenTry →0.15
RimeTry →0.00
Try →0.00
Hume0.00
0.000.250.500.751.00

Cost

lower is better

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