Speech to Text
Upload a recording or a video and get SRT or VTT subtitles or plain text to edit and download.
Drop an audio file here
MP3, M4A, WAV, FLAC, OGG, AAC… · up to 100 MB per file
Files are deleted after 2 hours. You can delete them right after downloading.
How to use Speech to Text in 3 steps
-
Choose a recording or video
Drop an MP3, M4A, WAV, FLAC, OGG, AAC or Opus file, or an MP4, MOV, MKV or WebM video, up to 100 MB. How many minutes per file are transcribed depends on your plan.
-
Pick the language and result
Leave Detect automatically on or pick the spoken language, then choose SRT, VTT or plain text. Type names of people and products into Names and terms so they are spelled right.
-
Edit and download
Press Transcribe. Click a line to edit it or a time to hear that part again, then download the file, translate it or have it read aloud with an AI voice.
Guides
A short read first gets you the right result on the first try.
Speech to Text Speech to text: subtitles and notes that need less fixing
How accurate a transcript is depends more on the recording than on the machine. Record well, list your names and terms, pick the right output, and there is far less to fix.
AI Art Generator AI Art Generator Free: Create Art from a Prompt
Describe the image you want, generate it in seconds, then refine your prompt until the artwork fits your idea.
Greeting Card Maker Diwali wishes: messages and greeting card ideas
Use these Diwali wishes as they are, or personalize them in a simple greeting card you can download as a PNG.
Features
Speech to Text listens to your recording or video and writes down what is said, as SRT or VTT subtitles with timings or as plain text for minutes and notes. It takes MP3, M4A, WAV, FLAC and MP4, MOV, MKV or WebM videos up to 100 MB, detects the language on its own and takes about as long to run as the recording lasts. The result opens on the page so you can fix any line before downloading.
- Takes MP3, M4A, WAV, FLAC, OGG, AAC and Opus audio, and MP4, MOV, MKV and WebM video up to 100 MB.
- Transcribes English, Vietnamese, Spanish, French, German, Italian, Portuguese, Russian, Japanese, Korean, Chinese, Hindi, Indonesian and Thai.
- SRT for YouTube, CapCut and Premiere, VTT for web players, or plain text with optional [mm:ss] marks.
- Names and terms help spell people and brands right; silence and noise are skipped.
- Edit any line and replay any part right on the page; downloads include your edits.
- Send the result on to Translate Text or Text to Speech; files are deleted after 2 hours.
Frequently asked questions
How long can the recording be?
Files can be up to 100 MB. How many minutes per file are transcribed depends on your plan: a longer file is still accepted, it is transcribed from the start up to your plan’s limit, and the page tells you where it stopped. Signing in for free gives you more minutes.
How do I get more accurate subtitles?
Use a clear recording with little background music. The language is detected from the first 30 seconds, so if the file opens with music, pick the language instead of Detect automatically. Type names and terms into the optional box, and fix any wrong line on the page before downloading.
What is the difference between SRT, VTT and plain text?
SRT and VTT are subtitles with a timing for every line: SRT is for YouTube, CapCut and Premiere, VTT for video players on the web. Plain text suits minutes, meeting notes and articles, and can start each paragraph with a [mm:ss] mark.
Are my recordings stored?
Your file and the result are deleted from BigQTools servers after 2 hours, and you can delete them right after downloading. BigQTools does not use your files to train AI.