GPT Transcribe

GPT Transcribe is an online AI speech to text tool that converts audio and video into transcripts with subtitles, speaker labels and timestamps. GPT Transcribe adds the layer that plain-text transcription models leave out: SRT and VTT subtitle files, speaker separation and word-level timing, all in the browser with no API key.

Key features:

• Upload audio or video, record live, or paste a media link.
• Supports MP3, WAV, M4A, MP4, MOV and WEBM files.
• Transcription in about 100 languages with automatic language detection, powered by OpenAI Whisper.
• Speaker diarization to separate who said what.
• Export as SRT, VTT, DOCX, JSON or TXT.
• A transcript editor, plus AI summaries and translation on higher plans.

Use cases:

• Video editors creating subtitle files for YouTube and social clips.
• Podcasters and journalists transcribing multi-speaker interviews.
• Teams turning meetings into searchable records.

Pricing: Every GPT Transcribe account opens with 5 free minutes; subscriptions add 1GB uploads, speaker labels and all export formats, and credit packs cover extra minutes.