whisper.cpp is an open-source implementation of OpenAI's Whisper speech recognition models, converted for efficient local and server-side inference. It allows developers to transcribe audio to text without cloud dependencies, supporting multiple model sizes and formats.
Whisper.cpp sits in PulseGate's Voice, TTS & speech category. It enables developers to perform accurate speech-to-text transcription locally or on servers without relying on cloud APIs. Whisper.cpp is an open-source project aimed at developers and researchers needing speech recognition. The project is open source (MIT). It runs on the web, the command line, and API, and it can be self-hosted.
Dakrd (fork of ggerganov) builds and maintains Whisper.cpp, and the product first shipped in 2022. The project is developed in the open on GitHub with 51.8k stars and 627 commits in the last 90 days. Across PulseGate's embedding index, Whisper.cpp has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are speech recognition, transcription, and local inference.
Latest indexed changes and source events
Dakrd/whisper.cpp discovered by the PulseGate indexer
Other apps tracked under the same category.
