← back to the directory
Library / SDK Inference & Serving

faster-whisper

1Fast 2Whisper 3speech-to-text 4using 5CTranslate2 6inference

the six Ws · specification

W1 Who

Maintained by SYSTRAN.

W2 What

Runs OpenAI Whisper speech-to-text far faster via CTranslate2.

W3 Where

A Python library on CPU or GPU.

W4 When

When transcribing audio efficiently in a pipeline.

W5 Why

Cuts Whisper latency and memory with quantized inference.

W6 With

CTranslate2, Whisper model weights, and optional GPU.

W7 Watch

Company-maintained; open-source (MIT). Runs fully locally on your hardware, so audio never leaves your machine.

Speech-to-textInferenceCTranslate2

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.