Text-to-Speech

Whether the voice says the right words for a number, date, currency amount or operator — a different question from drift, which is whether it sounds like itself across repeats.

ElevenLabseleven_v4Try →0.90

ElevenLabseleven_v4_turboTry →0.90

Gemini3.8-flash-lite-ttsTry →0.73

Gemini3.8-flash-ttsTry →0.70

Gemini3.1-flash-tts-previewTry →0.69

Inworldtts-2Try →0.61

Inworldtts-2-flashTry →0.58

Sonioxtts-rt-v2Try →0.49

xAI Grokgrok-ttsTry →0.45

OpenAIgpt-4o-mini-ttsTry →0.44

Sonioxtts-rt-v10.35

Rimearcanav3Try →0.35

NariQwen3-TTSTry →0.32

NariQwen3-TTS FastTry →0.30

ElevenLabseleven_v3_conversationalTry →0.30

HopperQwen3-TTS0.29

GradiumTTSTry →0.27

Smallestlightning_v3.1Try →0.25

Paxatts-flash-v1Try →0.25

Humeoctave-2Try →0.24

BlandspeechTry →0.22

Speechifysimba-3.2Try →0.21

Cartesiasonic-3.6Try →0.21

DeepgramfluxTry →0.20

Deepgramaura-2Try →0.20

Cartesiasonic-3.5Try →0.18

Fish Audios2.1-proTry →0.17

Palabratts-v1Try →0.16

MiniMaxspeech-2.8-hdTry →0.15

Qwenqwen3-tts-flashTry →0.15

0.000.250.500.751.00

What a vendor charges to synthesize a million characters of text, at its published list rate.

$0$25$50$75$100

$4

$5

$6

$10

$10

$10

$10

$10

$12

$13

$13

$15

$15

$15

$15

$18

$20

$20

$25

$30

$30

$33

$40

$40

$40

$45

$50

$50

$50

$50

$50

$50

$50

$50

$50

$58

$60

$60

$80

$100

$100

$100

$100

$100

Maya2 NativeNariQwen3-TTSHopperQwen3-TTSGemini3.8-flash-lite-ttsSpeechifysimba-3.2Qwenqwen3-tts-flashNariQwen3-TTS FastPaxatts-flash-v1Palabratts-v1Sonioxtts-rt-v1Sonioxtts-rt-v2Gemini3.8-flash-ttsInworldtts-2-flashFish Audios2.1-proxAI Grokgrok-ttsSmallestlightning_v3.1Smallestlightning_v3.1_proOpenAIgpt-4o-mini-ttsInworldtts-2Deepgramaura-2Rimemistv3Gemini3.1-flash-tts-previewElevenLabseleven_v4_turboRimearcanav3BlandspeechDeepgramfluxElevenLabseleven_v3_conversationalCartesiasonic-3.5Cartesiasonic-3.6ElevenLabseleven_flash_v2_5ElevenLabseleven_turbo_v2_5ElevenLabseleven_flash_v2ElevenLabseleven_turbo_v2Cartesiasonic-3RimecodaGradiumTTSMiniMaxspeech-2.6-turboMiniMaxspeech-2.8-turboElevenLabseleven_v4MiniMaxspeech-2.8-hdHumeoctave-2ElevenLabseleven_multilingual_v2Humeoctave-1MiniMaxspeech-2.6-hd