Prerequisites
Completed the Installation guide
Your First Transcription
Transcribe an Audio File
Call the
transcribe() method with your audio file:Audio files must be in WAV format, 16kHz sample rate, mono channel. See Audio Formats for details.
Complete Example
Here’s a full React Native component that transcribes an audio file:Using bundled assets
Using bundled assets
If you want to bundle the model and audio files with your app:
- Add
.binto Metro config (see Installation) - Use
require()instead of file paths:
Common Options
Language code (e.g., ‘en’, ‘es’, ‘fr’) or ‘auto’ for automatic detection
Translate speech to English
Number of CPU threads to use (2 for 4-core devices, 4 for more)
Beam search size for better accuracy (higher = more accurate but slower)
Callback function for transcription progress (0-100)
Next Steps
Core Concepts
Learn about contexts and audio formats
Features
Explore transcription, VAD, and realtime features
Examples
See more code examples and patterns
API Reference
View complete API documentation
Troubleshooting
Model file not found
Model file not found
Error:
Error: Model file not foundSolution: Verify the model file path is correct. If using require(), ensure the file exists in your project and Metro config includes .bin extensions.Audio format error
Audio format error
Error:
Error: Invalid audio formatSolution: Ensure your audio file is:- WAV format
- 16kHz sample rate
- Mono channel (1 channel)
- 16-bit PCM encoding
ffmpeg -i input.mp3 -ar 16000 -ac 1 -c:a pcm_s16le output.wavSlow transcription
Slow transcription
Problem: Transcription takes too longSolution (iOS): Enable Core ML acceleration (see Core ML Setup)Solution (General):
- Use a smaller or quantized model (e.g.,
tinyorbase-q8_0) - Increase
maxThreads(try 4) - Test in Release mode, not Debug mode
Memory issues on iOS
Memory issues on iOS
Error: App crashes with large modelsSolution: Enable Extended Virtual Addressing capability in Xcode:
- Open your iOS project in Xcode
- Select your app target
- Go to Signing & Capabilities
- Add “Extended Virtual Addressing” capability