https://blog.e-infra.cz/tags/speech-to-text/ Recent content in Speech-to-Text on e-INFRA CZ Blog Hugo en Copyright © e-INFRA CZ Thu, 22 Oct 2026 08:00:00 +0000 https://blog.e-infra.cz/blog/whisper/ Thu, 22 Oct 2026 08:00:00 +0000 https://blog.e-infra.cz/blog/whisper/ <h2 id="transcribing-speech-with-whisper-on-e-infra-cz" class="heading">Transcribing Speech with Whisper on e-INFRA CZ<a href="#transcribing-speech-with-whisper-on-e-infra-cz" aria-labelledby="transcribing-speech-with-whisper-on-e-infra-cz"> <!-- <i class="fas fa-link anchor"></i> --> <svg class="svg-inline--fa fas fa-link anchor" fill="currentColor" aria-hidden="true" role="img" viewBox="0 0 640 512"><use href="#fas-link"></use></svg>&nbsp; </a> </h2> <p>The <a href="https://blog.e-infra.cz/blog/chat-ai/">CERIT-SC AI tools</a> have offered large language models through a chat interface and an OpenAI-compatible API since 2025. Since May 2026, the same API has also offered speech recognition: the CERIT-SC team deployed OpenAI&rsquo;s <code>whisper-large-v3</code>, and in our first test it transcribed 103 seconds of Czech speech in about five seconds.</p>