About this tool

Speech Text is an online AI speech to text workspace that converts audio, video, live browser recordings, and media URLs into editable transcripts. Speech Text runs on OpenAI Whisper technology and supports over 100 languages with automatic detection or manual selection. Users upload MP3, WAV, M4A, MP4, and similar files, record directly in the browser, or paste a media link, then review the transcript, search it, correct wording, and apply speaker labels. Finished transcripts export as TXT, SRT, VTT, DOCX, JSON, or PDF for documents, subtitles, and searchable archives. Speech Text starts free with 5 transcription minutes, and paid plans add 1GB uploads, transcript editing, AI summaries, transcript chat, and translation into 100+ languages.