Skip to content
@SoundsGoodAI

SoundsGoodAI

SoundsGoodAI

Voice intelligence that helps AI connect with people.

SoundsGoodAI builds open-source infrastructure for fast, accurate, and efficient speech processing.

Open-source projects

Batched offline speech recognition for NVIDIA GPUs. Raw audio in, text and word timestamps out through one Python API.

It supports Zipformer and NVIDIA Parakeet models using TensorRT engines, native CUDA plugins, GPU feature extraction, and batched GPU decoding.

GitHub · PyPI

High-performance Silero voice activity detection for CPUs. It combines a streamlined ONNX graph with an optimized spectral frontend to improve throughput while preserving numerically equivalent speech probabilities.

It supports Linux and macOS on both x86-64 and ARM64 systems.

GitHub · PyPI

Follow our work

Pinned Loading

  1. fast-silero-vad fast-silero-vad Public

    High-throughput Silero VAD inference for CPU with multi-window ONNX execution and an optimized RFFT frontend.

    Python 16

  2. fast-gpu-asr fast-gpu-asr Public

    High-throughput batched ASR for NVIDIA GPUs. Run Zipformer and NVIDIA NeMo Parakeet models through one Python API with TensorRT, custom CUDA plugins, GPU beam search, and word timestamps - up to 25…

    Python 18

Repositories

Showing 3 of 3 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…