Gradium AI has launched a new default text-to-speech (TTS) model, boasting an 81.0% human-rated pass rate on a challenging set of sentences across five languages. This performance surpasses competitors like Cartesia Sonic 3.6 and ElevenLabs v3 Conversational. The model also achieves a fast time-to-first-audio of 216 ms with minimal variance, making it suitable for immediate deployment in voice agent applications. AI
IMPACT This new TTS model could improve the performance of voice agents in handling complex information like order numbers and callback digits.
RANK_REASON The article describes a new model release from a company, but it is not a frontier AI lab.
- Cartesia Sonic 3.6
- Coval
- ElevenLabs v3 Conversational
- Fish Audio S2.1 Pro
- Gradium AI
- Gradium TTS
- Hugging Face
- Inworld TTS 1.5 Max
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →