Subtitle Generator
Turn audio or video into timed SRT/VTT subtitles.
Audio is processed on our server to create timed captions and is not stored. Best with clips under ~10 minutes.
About Subtitle Generator
Upload an audio or video file (or record straight from your mic) and VoxAloud transcribes it with OpenAI's Whisper model, then turns the timed segments into ready-to-use SRT or VTT subtitle files. It auto-detects the language and works in 90+ languages — perfect for captioning YouTube videos, TikToks and courses.
- 1Upload audio/video or record your voice.
- 2Pick a language or leave it on auto-detect.
- 3Generate, then download timed SRT or VTT captions.
FAQ
What subtitle formats can I export?
SRT and VTT — both are widely supported by YouTube, video editors and web players.
Does it add timestamps automatically?
Yes — each caption gets accurate start and end times from the transcription.
Which languages are supported?
90+ languages with automatic language detection, powered by Whisper.
Is my file stored?
No — the audio is processed to create the captions and is not saved.