Start building →OverviewMultilingualVoices

Text-to-Speech · Multilingual

German

Language

Request a new language

Tell us which language you want added to this benchmark.

Benchmarks

X
Y
200ms400ms600ms1200140016001800Time to first audio lower is betterNaturalness higher is betterElevenLabs eleven_v3_conversationalxAI Grok ttsSoniox tts-rt-v1Soniox tts-rt-v2Hume octave-2Cartesia sonic-3.5Inworld tts-2Qwen qwen3-tts-flashMiniMax speech-2.8-hdOpenAI gpt-4o-mini-ttsRime arcanav3Smallest lightning_v3.1Gradium TTSDeepgram aura-2speko.ai/benchmarks

Naturalness

higher is better

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

field averagetied with bestDeepgramaura-21062GradiumTTS1245SmallestSmallestlightning_v3.11254RimeRimearcanav31257OpenAIgpt-4o-mini-tts1497MiniMaxMiniMaxspeech-2.8-hd1528QwenQwenqwen3-tts-flash1573InworldInworldtts-21576SpeechifySpeechifysimba-3.51608Cartesiasonic-3.51665HumeHumeoctave-21687Sonioxtts-rt-v21700Sonioxtts-rt-v11717xAI Groktts1762ElevenLabseleven_v3_conversational1798
80010001200140016001800

Time to first audio

lower is better

The pause the caller hears before the agent starts speaking.

InworldInworldtts-2118ms · 132ms
Deepgramaura-2121ms · 128ms
Cartesiasonic-3.5172ms · 239ms
SmallestSmallestlightning_v3.1175ms · 213ms
RimeRimearcanav3238ms · 245ms
xAI Groktts247ms · 276ms
ElevenLabseleven_v3_conversational261ms · 308ms
GradiumTTS274ms · 284ms
MiniMaxMiniMaxspeech-2.8-hd318ms · 350ms
Sonioxtts-rt-v1404ms · 441ms
QwenQwenqwen3-tts-flash411ms · 436ms
Sonioxtts-rt-v2418ms · 458ms
HumeHumeoctave-2455ms · 646ms
ElevenLabseleven_v3536ms · 590ms
OpenAIgpt-4o-mini-tts594ms · 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 Groktts1.00
Speechify1.00
0.97
0.97
0.97
Google Chirp0.95
0.94
Inworld0.90
0.75
0.65
Speechify0.55
MiniMax0.55
0.40
Qwen0.15
Rime0.00
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

$10
$13
$13
$15
$18
$20
$20
$25
$30
$33
$40
$50
$50
$58
$58
$100
$100
QwenQwenqwen3-tts-flashSonioxtts-rt-v1Sonioxtts-rt-v2xAI GrokttsSmallestSmallestlightning_v3.1OpenAIgpt-4o-mini-ttsSpeechifySpeechifysimba-3.5InworldInworldtts-2Deepgramaura-2GeminiGemini3.1-flash-tts-previewRimeRimearcanav3ElevenLabseleven_v3_conversationalCartesiasonic-3.5GradiumdefaultGradiumTTSHumeHumeoctave-2MiniMaxMiniMaxspeech-2.8-hd