Voxtral-Mini-4B-Realtime-2602-gguf is an open-source automatic speech recognition (ASR) model supporting 13 languages. It enables developers to transcribe audio to text locally using the GGUF format and integrates with tools like transcribe.cpp. Ideal for building multilingual ASR solutions.
In the Voice, TTS & speech space, Voxtral Mini 4B Realtime 2602 takes a focused approach. It focuses on transcribing spoken audio into text efficiently across multiple languages using local inference. Voxtral Mini 4B Realtime 2602 is an open-source project aimed at developers building speech-to-text or ASR applications. The project is open source (MIT). The product ships for the command line, and it can be self-hosted.
Behind Voxtral Mini 4B Realtime 2602 is Memoravox, and the product first shipped in 2026. The project is developed in the open on GitHub with 176 stars and 458 commits in the last 90 days. Across PulseGate's embedding index, Voxtral Mini 4B Realtime 2602 has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are speech recognition, multilingual support, and streaming transcription.
Latest indexed changes and source events
memoravox/Voxtral-Mini-4B-Realtime-2602-gguf discovered by the PulseGate indexer
Other apps tracked under the same category.