Tabla de clasificación de la Arena de voz controladaArtificial Analysis

Compara modelos de texto a voz (TTS) usando las mismas 8 voces clonadas (4 de EE. UU., 4 del Reino Unido).

Range
Creator
Model
Elo
95% CI
Samples
Lanzamiento
Precio de API 1
11-2
Cartesia logoCartesia
Sonic 3.6
1117-16/161,797Aug 202649,0 US$ /1 M de caracteres
21-2
Inworld logoInworld
Realtime TTS-2
1110-16/161,626Aug 202620,8 US$ /1 M de caracteres
33
Cartesia logoCartesia
Sonic 3.5
1088-13/133,451May 202649,0 US$ /1 M de caracteres
44
Inworld logoInworld
Realtime TTS-2 Flash
1071-15/151,623Aug 202610,4 US$ /1 M de caracteres
55-7
ElevenLabs logoElevenLabs
Eleven v3
1048-13/132,997Feb 2026100,0 US$ /1 M de caracteres
65-7
StepFun logoStepFun
StepAudio 2.5 TTS
1045-14/142,362Apr 202685,0 US$ /1 M de caracteres
75-9
SpaceXAI logoSpaceXAI
SpaceXAI TTS
1036-14/142,317Mar 202615,0 US$ /1 M de caracteres
87-10
ElevenLabs logoElevenLabs
v3 Conversational
1025-15/151,525Aug 202650,0 US$ /1 M de caracteres
97-10
MiniMax logoMiniMax
Speech 2.8 HD
1024-13/132,870Feb 2026100,0 US$ /1 M de caracteres
109-14
MiniMax logoMiniMax
Speech 2.8 Turbo
1012-13/132,963Feb 202660,0 US$ /1 M de caracteres
1110-18
SpeechifyAI logoSpeechifyAI
Simba 3.0
1009-14/142,263Feb 20266,6 US$ /1 M de caracteres
1210-19
BreezeBlue logoBreezeBlue
Breeze TTS 2Hugging FaceOpen Weights
1007-15/151,635Aug 202634,0 US$ /1 M de caracteres
1310-19
ElevenLabs logoElevenLabs
Multilingual v2
1004-13/132,850Aug 2023100,0 US$ /1 M de caracteres
1414
Fish Audio logoFish Audio
OpenAudio S1
10000/04,767Jun 202515,0 US$ /1 M de caracteres
1510-20
Fish Audio logoFish Audio
OpenAudio S1 MiniHugging FaceOpen Weights
998-14/142,257Jun 202515,0 US$ /1 M de caracteres
1611-20
Mistral logoMistral
Voxtral TTSHugging FaceOpen Weights
997-14/142,204Mar 202616,0 US$ /1 M de caracteres
1711-20
Fish Audio logoFish Audio
Fish Audio S2.1 Pro
997-14/142,249Jun 202615,0 US$ /1 M de caracteres
1811-20
Gradium logoGradium
Gradium TTS (Aug 2026)
996-15/151,768Aug 202647,2 US$ /1 M de caracteres
1913-20
Fish Audio logoFish Audio
Fish Audio S2 ProHugging FaceOpen Weights
993-13/133,432Mar 202615,0 US$ /1 M de caracteres
2014-20
Fish Audio logoFish Audio
Fish Audio S1
989-13/132,978Oct 202515,0 US$ /1 M de caracteres
2121-23
ElevenLabs logoElevenLabs
Flash v2.5
974-13/132,898Dec 202450,0 US$ /1 M de caracteres
2221-23
ElevenLabs logoElevenLabs
Turbo v2.5
972-14/142,392Jul 202450,0 US$ /1 M de caracteres
2321-23
KugelAudio logoKugelAudio
Kugel 3
965-13/133,636Jun 2026N/D
2424-25
Boson AI logoBoson AI
Higgs Audio V3 TTSHugging FaceOpen Weights
946-14/142,017Jun 202615,0 US$ /1 M de caracteres
2524-27
Cartesia logoCartesia
Sonic 3
936-14/142,488Oct 202549,0 US$ /1 M de caracteres
2625-30
Resemble AI logoResemble AI
ChatterboxGitHubOpen Weights
926-14/142,415May 202525,0 US$ /1 M de caracteres
2725-30
NVIDIA logoNVIDIA
Magpie TTS ZeroshotOpen Weights
924-17/17892Jul 2026N/D
2825-30
Krafton logoKrafton
Raon SpeechLM
921-15/151,615Apr 2026N/D
2926-30
Soniox logoSoniox
Soniox TTS Real-Time v2
918-15/151,680Aug 202614,2 US$ /1 M de caracteres
3026-30
Noiz logoNoiz
Noiz TTS
916-15/151,981Nov 2025N/D
3131
Smallest.ai logoSmallest.ai
Lightning v3.1
886-15/152,064Mar 202625,0 US$ /1 M de caracteres
3232
Coqui logoCoqui
829-16/162,249Nov 202340,4 US$ /1 M de caracteres
3333
OpenVoice logoOpenVoice
OpenVoice v2Hugging FaceOpen Weights
784-17/171,973Apr 20248,3 US$ /1 M de caracteres

1 El precio de API refleja el costo de generar 1M de caracteres en la API del creador del modelo con la configuración predeterminada del modelo