Language Support
FloWords supports 99+ languages through the Whisper models. This guide covers language configuration, auto-detection, and tips for multilingual transcription.
Supported Languages
Section titled “Supported Languages”Tier 1: Excellent Support
Section titled “Tier 1: Excellent Support”These languages have the highest accuracy and are well-tested:
| Language | Code | Notes |
|---|---|---|
| English | en | Best support, use .en models |
| Spanish | es | Excellent accuracy |
| French | fr | Very good support |
| German | de | Very good support |
| Italian | it | Very good support |
| Portuguese | pt | Including Brazilian |
| Dutch | nl | Good support |
| Russian | ru | Good support |
| Japanese | ja | Good support |
| Chinese | zh | Mandarin, good support |
| Korean | ko | Good support |
Tier 2: Good Support
Section titled “Tier 2: Good Support”Solid accuracy for most use cases:
| Language | Code |
|---|---|
| Arabic | ar |
| Czech | cs |
| Danish | da |
| Finnish | fi |
| Greek | el |
| Hebrew | he |
| Hindi | hi |
| Hungarian | hu |
| Indonesian | id |
| Norwegian | no |
| Polish | pl |
| Romanian | ro |
| Swedish | sv |
| Thai | th |
| Turkish | tr |
| Ukrainian | uk |
| Vietnamese | vi |
Tier 3: Basic Support
Section titled “Tier 3: Basic Support”Available but may have lower accuracy:
Click to see all 99+ supported languages
Afrikaans, Albanian, Amharic, Armenian, Azerbaijani, Bashkir, Basque, Belarusian, Bengali, Bosnian, Breton, Bulgarian, Burmese, Cantonese, Catalan, Croatian, Estonian, Faroese, Galician, Georgian, Gujarati, Haitian, Hausa, Hawaiian, Icelandic, Javanese, Kannada, Kazakh, Khmer, Lao, Latin, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Occitan, Pashto, Persian, Punjabi, Sanskrit, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Sundanese, Swahili, Tagalog, Tajik, Tamil, Tatar, Telugu, Tibetan, Turkmen, Urdu, Uzbek, Welsh, Yiddish, Yoruba…
Setting Your Language
Section titled “Setting Your Language”Fixed Language Mode
Section titled “Fixed Language Mode”Set a specific language for consistent results:
- Open Settings (⌘,)
- Go to Model tab
- Find Language dropdown
- Select your language
- Close Settings
- Click FloWords menu bar icon
- Look for language indicator
- Click to change language
Auto-Detection Mode
Section titled “Auto-Detection Mode”Let Whisper detect the language automatically:
- Go to Settings > Model
- Set Language to Auto or Detect
- Whisper will identify the language per recording
English-Optimized Models
Section titled “English-Optimized Models”For English-only users, FloWords offers .en models:
| Model | Standard | English-Only |
|---|---|---|
| Tiny | tiny | tiny.en |
| Base | base | base.en |
| Small | small | small.en |
| Medium | medium | medium.en |
Benefits of .en Models
Section titled “Benefits of .en Models”- Faster: No language detection overhead
- More Accurate: Optimized specifically for English
- Smaller: Slightly smaller file sizes
Multilingual Transcription
Section titled “Multilingual Transcription”Mixed Language Content
Section titled “Mixed Language Content”If your recording contains multiple languages:
- Set language to Auto-Detect
- Use a Large model for best accuracy
- Review results for language switches
- Manually correct if needed
Limitations
Section titled “Limitations”- Rapid language switching may confuse the model
- Heavily mixed content (code-switching) is challenging
- Some language pairs work better than others
Best Practices
Section titled “Best Practices”- Try to separate content by language when possible
- Use explicit language setting when one language dominates
- Larger models handle mixed content better
Regional Variations
Section titled “Regional Variations”English Variants
Section titled “English Variants”Whisper handles various English accents:
- American English
- British English
- Australian English
- Indian English
- South African English
For best results with strong accents, use larger models.
Spanish Variants
Section titled “Spanish Variants”Supports regional Spanish:
- Castilian (Spain)
- Latin American Spanish
- Mexican Spanish
Chinese Variants
Section titled “Chinese Variants”- Mandarin (best support)
- Cantonese (basic support)
Portuguese Variants
Section titled “Portuguese Variants”- European Portuguese
- Brazilian Portuguese
Language-Specific Tips
Section titled “Language-Specific Tips”English
Section titled “English”- Use
.enmodels for best performance - Small.en offers excellent balance
- Technical terms: add to Custom Dictionary
Spanish
Section titled “Spanish”- Set language explicitly (es)
- Medium model recommended
- Regional vocabulary may need dictionary additions
Japanese
Section titled “Japanese”- Larger models significantly improve accuracy
- Consider cloud providers for complex content
- Technical terms often in English
Chinese
Section titled “Chinese”- Mandarin has better support than Cantonese
- Large model recommended
- May need post-processing for tone marks
Arabic
Section titled “Arabic”- Right-to-left output handled correctly
- Large model recommended for dialectal Arabic
- Modern Standard Arabic best supported
Troubleshooting
Section titled “Troubleshooting”Wrong Language Detected
Section titled “Wrong Language Detected”Symptoms: Text appears in wrong language or script
Solutions:
- Set language explicitly instead of auto-detect
- Check audio doesn’t have mixed languages
- Use a larger model
Poor Accuracy in My Language
Section titled “Poor Accuracy in My Language”Symptoms: Many errors, garbled output
Solutions:
- Use Medium or Large model
- Check audio quality
- Reduce background noise
- Speak more clearly
- Try a cloud provider
Missing Characters or Scripts
Section titled “Missing Characters or Scripts”Symptoms: Characters display as boxes or question marks
Solutions:
- Ensure your Mac has appropriate fonts
- Check system language settings
- Copy text to a Unicode-capable application
Accents Causing Problems
Section titled “Accents Causing Problems”Symptoms: Strong accents poorly transcribed
Solutions:
- Use larger models
- Speak slightly slower
- Consider cloud providers with accent support
- Add common mispronunciations to dictionary
Language Selection Guide
Section titled “Language Selection Guide”By Use Case
Section titled “By Use Case”| Use Case | Recommendation |
|---|---|
| Single language, English | Use .en model |
| Single language, other | Set language explicitly |
| Occasional mixing | Auto-detect + large model |
| Professional multilingual | Consider cloud providers |
By Accuracy Need
Section titled “By Accuracy Need”| Accuracy Need | Model | Language Setting |
|---|---|---|
| Quick notes | Tiny/Base | Explicit |
| Standard use | Small | Explicit |
| Professional | Medium/Large | Explicit |
| Mixed content | Large | Auto-detect |
Future Language Support
Section titled “Future Language Support”Whisper continues to improve, and FloWords will support new language capabilities as they become available. Updates include:
- Improved accuracy for existing languages
- Better handling of accents and dialects
- Enhanced mixed-language support
Next Steps
Section titled “Next Steps”- Configure Local Models for your language
- Add Custom Dictionary for specialized terms
- Set Up AI Enhancement for post-processing