daily-hour-news·
🛠️Phonon TTS Hits 28 ms First Audio in a 65 MB Model
TL;DR
Gradium's Phonon TTS ships in 65 MB and 75 MB sizes and streams first audio in 28 ms on CPU. The English 31m model is Apache 2.0, while the five-language 40m model is non-commercial, so check the license first.
Gradium's Phonon TTS ships in 65 MB and 75 MB sizes and streams first audio in 28 ms on CPU. The English 31m model is Apache 2.0, while the five-language 40m model is non-commercial, so check the license first.
Key Points
1
Two sizes, about 65 MB and 75 MB; English, French, German, Spanish, Portuguese; 100+ built-in voices
Keep reading — it's free
Enter your email to keep reading — plus the best of AI & tech, daily. Free, forever.
Also get
or
Already a member? Sign in
Quick Facts
Phonontext-to-speechGradiumon-device AIApache 2.0Hugging Facelatency
Comments
Subscribe to join the conversation...
Be the first to comment