Sonic 3.5 currently leads the Text to Speech Arena with an Elo score of 1218.

The top Text to Speech models by Elo rating are: 1. Sonic 3.5 (Elo 1218), 2. Gemini 3.1 Flash TTS (Elo 1216), 3. Fun-Realtime-TTS (Elo 1210), 4. Realtime TTS-2 - Research Preview (Elo 1202), 5. xAI Text to Speech (Elo 1197). 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 1063. 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 1113. There are 15 open weights models out of 86 total.

The top 5 open weights Text to Speech models are: 1. Step Audio EditX (Mar 2026) (Elo 1113), 2. Fish Audio S2 Pro (Elo 1111), 3. Voxtral TTS (Elo 1075), 4. Kokoro 82M v1.0 (Elo 1063), 5. Magpie-Multilingual 357M (Feb 2026) (Elo 1056).

You can filter by the following categories: Knowledge Sharing, Assistants, Entertainment, and Customer Service, and the following accents: US and UK.