Sakhanda Wire
NVDA $152.56 -2.29% MSFT $505.79 -2.36% GOOGL $279.70 -1.42% META $618.14 -1.32% AMZN $256.03 -0.67%
← Back to the news

Sonic-3.6 Leads Two Speech Synthesis Leaderboards

Cartesia has released Sonic-3.6, the latest version of its real-time text-to-speech model, about three months after Sonic-3.5. The system is ranked first on both Artificial Analysis speech leaderboards, with 1,283 Elo on Provider Voice and 1,123 on Controlled Voice. The latter evaluates models using the same eight reference voices; Sonic-3.5 ranks second and ElevenLabs Eleven v3 third.

Sonic-3.6 is built on state space models rather than transformers. Cartesia reports time-to-first-audio below 90 milliseconds, while noting that this is model latency rather than a measured end-to-end round trip. The model is available in beta through a hosted API, but not as self-hosted weights; it is a closed commercial product.

The API includes expression tags, voice cloning from about 10 seconds of audio, pronunciation dictionaries, and controls for speed, volume, and emotion. Artificial Analysis lists a normalized price of $49.00 per 1M characters, compared with $100.00 for ElevenLabs Eleven v3 and $10.00 for Speechify Simba 3.2. Cartesia’s Scale plan costs $299 per month and includes roughly 10,667 TTS minutes and 15 concurrent requests.

Written by Sakhanda Wire AI from reporting by MarkTechPost. Facts, quotes and full context are in the original article below.

Originally published by MarkTechPost on

Read the original on MarkTechPost ↗

The reporting and the image belong to MarkTechPost and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news