All features
Speech to text
Speech to text
Turn audio into accurate text in seconds.
Transcribe audio and video files with Whisper and QTstt for fast, accurate speech-to-text in Persian and dozens of other languages.
Sample transcription
Upload: meeting.mp3 (72 minutes)
Full transcript ready — text plus timestamped export.
Use cases
For whatever you have in mind.
Meeting transcripts
Convert internal meetings, interviews, and calls into searchable text and structured notes.
Video subtitles
Generate transcript files and subtitle outputs for educational, marketing, and media workflows.
Voice-message workflows
Turn voice notes into text for messaging, CRM, support, and archive systems.
Available models
Choose from the world's best models.
WhisperOpenAI transcription across 99 languages with strong accuracy.
QTsttChatQT's Persian-optimized speech-to-text route for everyday spoken language.Start with free sign-up.
Add credit as you need it — every model and feature in one wallet.
FAQ
Answers at a glance.
Which formats are supported?
Common formats such as MP3, MP4, WAV, M4A, OGG, and WebM are typical inputs, depending on the tool path.
How accurate is Persian transcription?
For clean files, Persian transcription accuracy is typically very high. QTstt is especially useful for colloquial Persian, while Whisper remains a strong multilingual baseline.
Are timestamps available?
Yes. Depending on the route, you can export plain text, structured JSON, or subtitle-style outputs with timestamps.
How long can a file be?
That depends on the plan and workflow, but longer recordings are supported in professional use cases.