Speech Text

Speech Text is an online speech to text AI workspace that transcribes audio to text and converts video to text. Speech Text handles uploaded files, live browser recordings and media URLs, then turns spoken content into editable transcripts you can search, review and export.

Key features:

• Upload audio or video, record in the browser, or process a media URL.
• Supports MP3, WAV, M4A, MP4, MOV and WEBM files.
• Transcription in 100+ languages, powered by OpenAI Whisper.
• Search, edit and correct transcripts in one focused flow.
• Export as TXT, SRT, DOCX or JSON.

Use cases:

• Meeting notes, interview copy and podcast drafts.
• Captions and subtitle files for video.
• Searchable archives of lectures, webinars, support calls and voice memos.

Pricing: Speech Text begins with 5 free minutes, then subscriptions add 1GB uploads, speaker labels, transcript editing and all exports, with credit packs for extra minutes.