Skip to content
FloWords

Audio File Transcription

FloWords can transcribe existing audio and video files, not just live recordings. Perfect for meetings, interviews, podcasts, and lectures.

Supported Formats

Section titled “Supported Formats”

Audio Files

Section titled “Audio Files”
FormatExtensionNotes
WAV.wavUncompressed, best quality
MP3.mp3Most common, widely compatible
M4A.m4aApple format, good compression
AAC.aacAdvanced audio coding
FLAC.flacLossless compression
AIFF.aiffApple lossless format
CAF.cafCore Audio Format

Video Files

Section titled “Video Files”
FormatExtensionNotes
MP4.mp4Most common video format
MOV.movApple QuickTime format

How to Transcribe Files

Section titled “How to Transcribe Files”

Method 1: Drag & Drop

Section titled “Method 1: Drag & Drop”
  1. Open FloWords (click menu bar icon or use shortcut)
  2. Drag your audio/video file onto the FloWords window
  3. Wait for transcription to complete
  4. Copy or save the result

Method 2: File Menu

Section titled “Method 2: File Menu”
  1. Open FloWords
  2. Click File > Transcribe Audio File (or press ⌘O)
  3. Select your file in the dialog
  4. Wait for transcription to complete
  5. Review and use the transcription

Method 3: Finder Context Menu

Section titled “Method 3: Finder Context Menu”
  1. Right-click your audio/video file in Finder
  2. Select Open With > FloWords
  3. FloWords opens and begins transcription
  4. Review results when complete

Transcription Options

Section titled “Transcription Options”

Model Selection

Section titled “Model Selection”

Choose your transcription model before processing:

Use: Tiny or Base models

  • Faster processing
  • Good for quick reviews
  • Lower accuracy on challenging audio

Language Settings

Section titled “Language Settings”

For best results, set the correct language:

  1. Go to Settings > Model
  2. Set Language to match your audio
  3. Or use Auto-Detect for multilingual content

Handling Long Files

Section titled “Handling Long Files”

File Length Considerations

Section titled “File Length Considerations”
DurationRecommendation
< 5 minutesAny model, fast processing
5-30 minutesSmall or Medium model
30-60 minutesConsider splitting or using cloud
> 1 hourSplit file or use cloud provider

Splitting Long Files

Section titled “Splitting Long Files”

For very long recordings:

  1. Use an audio editor (Audacity, GarageBand)
  2. Split into 30-minute segments
  3. Transcribe each segment
  4. Combine results

Progress Tracking

Section titled “Progress Tracking”

During transcription:

  • Progress bar shows completion percentage
  • Estimated time remaining displayed
  • Cancel button available if needed

Tips for Better Results

Section titled “Tips for Better Results”

Audio Quality

Section titled “Audio Quality”

Clear Audio

Clean recordings transcribe better. Reduce background noise when possible.

Single Speaker

Single-speaker content is easier to transcribe accurately.

Standard Speed

Normal speaking pace provides best results.

Good Volume

Avoid audio that’s too quiet or clipping.

Preprocessing Tips

Section titled “Preprocessing Tips”
  • Remove silence at the beginning/end
  • Normalize audio to consistent volume
  • Reduce noise if heavily distorted
  • Convert unusual formats to WAV or MP3

Post-Processing

Section titled “Post-Processing”

After transcription:

  1. Review for obvious errors
  2. Use AI Enhancement to fix grammar
  3. Add punctuation if needed
  4. Format as required (paragraphs, lists, etc.)

Use Cases

Section titled “Use Cases”

Meeting Transcription

Section titled “Meeting Transcription”
  1. Record meeting with Voice Memos or similar
  2. Export as M4A or MP3
  3. Drag into FloWords
  4. Get full meeting transcript
  5. Share with attendees

Interview Processing

Section titled “Interview Processing”
  1. Record interview (external recorder or phone)
  2. Transfer file to Mac
  3. Open in FloWords
  4. Transcribe with Large model for accuracy
  5. Edit and format as needed

Podcast Notes

Section titled “Podcast Notes”
  1. Download podcast episode
  2. Transcribe in FloWords
  3. Use AI Enhancement to summarize
  4. Create show notes or highlights

Lecture Capture

Section titled “Lecture Capture”
  1. Record lecture (with permission)
  2. Transcribe after class
  3. Use as study notes
  4. Search for specific topics

Batch Processing

Section titled “Batch Processing”

Currently, FloWords processes files one at a time. For multiple files:

  1. Queue files by adding them one after another
  2. Wait for each to complete
  3. Review results individually

Output Options

Section titled “Output Options”

Copy to Clipboard

Section titled “Copy to Clipboard”

Click Copy button to copy transcription text to clipboard.

Save to File

Section titled “Save to File”

Click Save to export as:

  • Plain text (.txt)
  • Markdown (.md)

Send to Enhancement

Section titled “Send to Enhancement”

Click Enhance to process with AI enhancement:

  • Fix grammar and spelling
  • Add punctuation
  • Format as desired

Troubleshooting

Section titled “Troubleshooting”

”Unsupported Format”

Section titled “”Unsupported Format””
  • Convert file to WAV or MP3
  • Use VLC or Audacity for conversion
  • Check file isn’t corrupted

”Processing Failed”

Section titled “”Processing Failed””
  • Try a smaller file first
  • Check available memory
  • Restart FloWords
  • Try a different model

”Low Accuracy Results”

Section titled “”Low Accuracy Results””
  • Use a larger model
  • Check audio quality
  • Set correct language
  • Consider cloud provider for difficult audio

”Taking Too Long”

Section titled “”Taking Too Long””
  • File may be very long
  • Switch to smaller model
  • Check Activity Monitor for issues
  • Consider splitting the file

Limitations

Section titled “Limitations”
  • File size: Very large files may take considerable time
  • Audio quality: Poor quality audio = poor transcription
  • Languages: Best results with supported languages
  • Specialized content: Technical jargon may need dictionary additions

Next Steps

Section titled “Next Steps”