Speech Text
AI speech to text for audio, video and live recordings
Speech Text is an online AI speech to text workspace that turns audio, video, live browser recordings, and media URLs into editable, searchable transcripts. Speech Text is powered by OpenAI Whisper technology and supports more than 100 languages, with automatic language detection or manual selection. Users upload MP3, WAV, M4A, MP4, MOV, or WEBM files, record directly in the browser, or paste a supported media link, then review the transcript, search it, fix wording, and apply speaker labels before exporting. Finished transcripts export as TXT, SRT, VTT, DOCX, JSON, or PDF for documents, subtitles, and searchable archives. Speech Text is freemium: new users get 5 free transcription minutes, and paid plans start at $4.90 per month billed yearly.
Features
Upload MP3, WAV, M4A, MP4, MOV, or WEBM files and transcribe them in the browser
Record speech live in the browser without a separate recorder app
Start a transcription from a media URL instead of downloading and re-uploading
Automatic language detection plus manual selection across 100+ languages
Speaker labels and timestamps for interviews, meetings, and panels
Searchable, editable transcript view for correcting wording before export
Exports in TXT, SRT, VTT, DOCX, JSON, and PDF
Pro AI tools: AI Summary, AI Analytics, chat with a transcript, and translation into 100+ languages
Use Cases
Journalists transcribe recorded interviews for articles and research
Podcasters turn episodes into show notes and blog drafts
Video editors generate SRT and VTT subtitle files for captions
Students and researchers capture lectures and webinars as searchable notes
Teams document meetings without replaying the recording
Support and operations teams archive calls as searchable text records
Comments
We built Speech Text because transcription usually means juggling three tools: a recorder, a transcription service, and a subtitle editor. Speech Text keeps upload, live browser recording, media URL import, transcript editing, and export in one page, running on OpenAI Whisper across 100+ languages. Would love feedback on the export formats — TXT, SRT, VTT, DOCX, JSON, and PDF are supported today, and we are curious which ones people actually use most.
Premium Products
Sponsors
Buy
Makers
Makers
Comments
We built Speech Text because transcription usually means juggling three tools: a recorder, a transcription service, and a subtitle editor. Speech Text keeps upload, live browser recording, media URL import, transcript editing, and export in one page, running on OpenAI Whisper across 100+ languages. Would love feedback on the export formats — TXT, SRT, VTT, DOCX, JSON, and PDF are supported today, and we are curious which ones people actually use most.
Premium Products
New to Fazier?
Find your next favorite product or submit your own. Made by @FalakDigital.
Copyright ©2025. All Rights Reserved