Speech Text

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 handles more than 100 languages, so multilingual meetings, interviews, and lecture recordings can be transcribed in one place instead of across several tools.

Key features
- Four ways to start a job: upload a file (MP3, WAV, M4A, MP4, MOV, WEBM), record live in the browser, paste a supported media URL, or run Whisper in-browser via WebGPU.
- Automatic language detection with manual override across 100+ languages.
- Speaker labels and timestamps for interviews, panels, and multi-person meetings.
- A transcript editor with full-text search for locating passages without replaying the recording.
- Exports in TXT, SRT, VTT, DOCX, JSON, and PDF for documents, subtitle work, and structured data.
- Pro AI tools including AI Summary, AI Analytics, chat with any transcript, translation into 100+ languages, and email delivery.

Use cases
Journalists transcribe interviews for articles. Podcasters repurpose episodes into show notes and blog drafts. Video editors generate SRT and VTT subtitle files. Students and researchers capture lectures and webinars as searchable notes. Support and operations teams archive calls as text records that can be searched later.

Pricing
Speech Text is freemium: new users get 5 free transcription minutes, and paid plans start at $4.90 per month billed yearly, with Pro at $14.90 and Max at $24.90 adding larger transcription allowances and the AI toolset.