Mejores modelos de texto a voz (TTS) con voces controladas

Compara la calidad, la velocidad y el precio de modelos de generación de voz utilizando las mismas voces clonadas para todos los modelos, lo que permite aislar la calidad del modelo de la selección de voz.

Para más detalles, consulta nuestra página de metodología.

Elo de calidad de la Arena de voces controladas: General

Arena Elo: average Elo rating of the model per language · Higher is better

Relative Elo score of the models as determined by responses from users in Artificial Analysis' Speech Arena. Some models may not be shown due to not yet having enough votes.

Calidad

Elo de calidad de la Arena de voces controladas

Arena Elo: average Elo rating of the model · Higher is better

Relative Elo score of the models as determined by responses from users in Artificial Analysis' Speech Arena. Some models may not be shown due to not yet having enough votes.

Precios

Precio

Price: USD per 1M characters of text · Lower is better

Price per 1M characters of text. For detail on how we calculate price for providers which price based on inference time or subscription plans, see our methodology page.

Factor de velocidad

Caracteres por segundo

Characters processed per second: # of characters per second of generation time · Higher is better

Number of characters processed per second of generation time. Higher values indicate faster generation speeds.