Overall Preference vs Speed
Top-left quadrant shows models with fast generation and high ratings
Overall Preference vs Price
Top-left quadrant shows models with low cost and high ratings
Top-left quadrant shows models with fast generation and high ratings
Top-left quadrant shows models with low cost and high ratings
Top-left quadrant shows models with fast generation and high ratings
Top-left quadrant shows models with low cost and high ratings
The most convincing AI speech and sound.
Google Gemini 3.8 Flash TTS
Google Gemini 3.1 Flash TTS
Google Gemini 2.5 Pro TTS
Eleven v4 Turbo
Eleven v4
Google Gemini 2.5 Flash TTS
Eleven v3
Grok TTS
OpenAI GPT Realtime 2
OpenAI GPT-4o Mini TTS
OpenAI GPT Realtime 2.1
MAI-Voice-2
Magpie TTS Multilingual
AI models converting text into natural-sounding speech.
Top-left quadrant shows models with fast generation and high ratings
Top-left quadrant shows models with low cost and high ratings
How models rank on specific tasks in this arena
Elo Rating: A skill-based rating system starting at 1200. Ratings are calculated using the standard Bradley-Terry model. See more in our Methodology page.Margin of Error: Shows ±standard error from the Bradley-Terry model for Elo rating confidence intervals.