Fun-Realtime-TTS currently leads the Text to Speech Arena with an Elo score of 1227.

The top Text to Speech models by Elo rating are: 1. Fun-Realtime-TTS (Elo 1227), 2. Gemini 3.1 Flash TTS (Elo 1217), 3. Realtime TTS-2 - Research Preview (Elo 1206), 4. Sonic 3.5 (Elo 1206), 5. Realtime TTS 1.5 Max (Elo 1199). 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 1064. Other affordable options include StyleTTS 2 at $2.82 per 1M characters.

Fish Audio S2 Pro is the highest-ranked open weights model on the Text to Speech Leaderboard with an Elo score of 1128. There are 15 open weights models out of 84 total.

The top 5 open weights Text to Speech models are: 1. Fish Audio S2 Pro (Elo 1128), 2. Step Audio EditX (Mar 2026) (Elo 1112), 3. Voxtral TTS (Elo 1070), 4. Kokoro 82M v1.0 (Elo 1064), 5. Magpie-Multilingual 357M (Feb 2026) (Elo 1059).

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