Category
Accent
Frequently Asked Questions
Inworld TTS 1.5 Max currently leads the Text to Speech Arena with an Elo score of 1217.
The top Text to Speech models by Elo rating are: 1. Inworld TTS 1.5 Max (Elo 1217), 2. Eleven v3 (Elo 1177), 3. Inworld TTS 1 Max (Elo 1173), 4. Inworld TTS 1.5 Mini (Elo 1163), 5. Speech 2.8 HD (Elo 1162). Rankings are based on blind user votes in the Speech Arena.
Models are ranked using an Elo rating system derived from user votes in blind comparisons in the Speech Arena. Users listen to pairs of speech samples generated from the same text and choose which sounds more natural. Higher Elo scores indicate a model produces speech preferred more often by listeners. Vote in the Speech Arena
Kokoro 82M v1.0 is the most affordable at $0.65 per 1M characters with an Elo score of 1056. Other affordable options include StyleTTS 2 at $2.82 per 1M characters.
Step Audio EditX (Mar 2026) is the highest-ranked open weights model on the Text to Speech Leaderboard with an Elo score of 1094. There are 12 open weights models out of 62 total.
The top open weights Text to Speech models are: 1. Step Audio EditX (Mar 2026) (Elo 1094), 2. Kokoro 82M v1.0 (Elo 1056), 3. Maya1 (Elo 1049).
You can filter by the following categories: Knowledge Sharing, Assistants, Entertainment, and Customer Service, and the following accents: US and UK.