• Subscribe
  • All activity
    Alexander Veysov
    Stellar quality.
    Highly portable.
    No strings attached.
    Supports 8 kHz and 16 kHz.
    Models < one megabyte in size.
    Supports 30, 60 and 100 ms chunks.
    Trained on 100+ languages, generalizes well.
    One chunk ~ 1ms on a single thread. ONNX up to 2-3x faster.
    Silero VAD
    Silero VAD
    One voice detector to rule them all
    Alexander Veysov
    Alexander Veysov
    left a comment
    Silero VAD is awesome. Just try it.
    Silero VAD
    Silero VAD
    One voice detector to rule them all
    Alexander Veysov
    Free, high-quality speech-to-text running fast on one CPU thread. Not middleware, no cloud required, no GAFA APIs. 10 Voices in 5 languages. Can be run locally on your PC / device / phone.
    Silero Text-To-Speech
    Silero Text-To-Speech
    High-Quality Text-To-Speech Running On 1 CPU Core Locally
    Alexander Veysov
    Silero provides pre-trained enterprise-grade STT models. Enterprise-grade STT made refreshingly simple (seriously, see our benchmarks). We provide quality comparable to Google's STT (and sometimes even better) and we are not Google.
    Silero.ai
    Silero.ai
    Pre-trained enterprise-grade STT and speech products