Typist
AI transcription for audio and video in seconds
Transcribe audio and video files to text using AI models from OpenAI, xAI, and ElevenLabs with up to 99% accuracy in over 100 languages.
About this launch
Typist is an AI-powered transcription platform that converts audio and video files to text using leading speech-to-text models. Users can choose between three transcription engines: Whisper v3 Turbo for speed and cost efficiency, Grok 2.0 for fast multi-speaker support, or Scribe v2 for highest accuracy in specialized domains like legal and medical work.
The service supports multiple audio and video formats including MP3, MP4, M4A, WAV, FLAC, OGG, and WebM, with file sizes up to 5 GB on paid plans. Transcripts can be exported to TXT, DOCX, PDF, SRT, and VTT formats. Free users get 60 minutes of transcription without requiring a credit card, while paid plans range from $6.99 to $49.99 monthly with varying credit allocations and features.
Typist offers additional tools including browser-based audio and video conversion, compression, extraction, splitting, and YouTube transcript generation. The platform also supports integration with AI assistants like ChatGPT and Claude for transcript analysis.
What it does
- Transcribe MP3, MP4, M4A, WAV, FLAC, OGG, and WebM formats
- Export to TXT, DOCX, PDF, SRT, and VTT formats
- Support for 99+ languages with Whisper models
- Connect ChatGPT or Claude for transcript analysis
- Transcription speeds up to 217× real-time with Whisper v3 Turbo
- Word-level timestamps in all transcript formats
- Free browser tools for audio/video conversion and compression
- Automatic YouTube transcript generation
- Up to 5 GB file size on paid plans
Pricing
Pricing model: Freemium
Free: 60 minutes (no card required). Lite: $6.99/mo (500 credits/month, or $70/year). Premium: $19.99/mo (4,500 credits/month). Max: $49.99/mo (15,000 credits/month). 1 credit = 1 minute on Whisper v3 Turbo; Grok 2.0 and Whisper v3 use 2 credits/minute; Scribe v2 uses 4 credits/minute.
Shopper questions
What files and formats can I transcribe?
Typist supports audio and video files in MP3, WAV, M4A, FLAC, OGG, MP4, and WebM formats. Free and paid plans support up to 500 MB and 5 GB per file respectively. A free Media Converter tool helps convert unsupported formats, and every transcript exports to TXT, DOCX, PDF, SRT, and VTT.
How long does a transcription take?
Whisper v3 Turbo processes audio at approximately 217× real-time speed, meaning a 90-minute podcast typically produces a draft transcript in under a minute. Whisper v3 is slightly slower at about 186× real-time because it performs more processing per second for better accuracy.
Which transcription model should I pick?
Grok 2.0 is most accurate for English, while Whisper v3 Turbo and Whisper v3 handle 99+ languages and are fast. Scribe v2 is built for difficult audio in publishing, legal, medical, and subtitle work. All models are available on every plan, including the free tier.
How accurate is the transcription?
Clean audio on Whisper v3 typically achieves word accuracy in the high-90s, while noisy multi-speaker recordings on Whisper v3 Turbo land in the low-90s. Recording quality is the biggest factor in accuracy. For the most difficult audio, Scribe v2 provides the best results.
Can I cancel anytime, and do you offer refunds?
Yes to both. Plans have no contracts or cancellation fees; users can cancel from their dashboard and keep access through the end of their paid period, then revert to Free with transcripts intact. Yearly subscribers can email for refunds on unused portions.
Typist has a free listing. The owner can unlock the full profile with a paid launch for $5:
- Founder story (locked)
- Milestones (locked)
- Demo video (locked)
- Dofollow website link (locked)
Shoppers also viewed
- v2md
Voice & transcription
- Shepit
Voice & transcription
- Saidwire
Voice & transcription
- SpeechText.AI
Voice & transcription
