cohere-transcribe-03-2026 is an open-source automatic speech recognition (ASR) model released by CohereLabs on Hugging Face. It enables developers to transcribe audio files into text using API or local inference. The model supports multiple languages and is suitable for building transcription services, voice assistants, and accessibility tools.
Cohere Transcribe 03 2026 sits in PulseGate's Speech to text category. It focuses on automating the conversion of spoken audio into accurate text for developers and AI applications. It is built as an open-source project for developers. The project is open source (Apache-2.0). Cohere Transcribe 03 2026 is available on the web, the command line, Android, and API.
Duplex Ltd. builds and maintains Cohere Transcribe 03 2026, and it first shipped in 2023. The project is developed in the open on GitHub with 83.2k stars and 2.7k commits in the last 90 days. Key capabilities include speech recognition, transcription, and open weights.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do