Help Center

We support all major audio formats, including MP3, WAV, M4A, AAC, WMA, OGG, FLAC, etc. The maximum file size limit is 500MB.

We use enterprise-grade encryption technology with end-to-end encryption for all uploaded audio files. Files are stored on our servers for no longer than 24 hours and are deleted immediately after conversion. Additionally, our servers are deployed in ISO 27001 certified data centers.

The free version allows up to 10 minutes of audio conversion per day, with a single file size limit of 20MB. It supports recognition of up to 3 languages and requires higher audio quality. Upgrade to the professional version to remove these limitations.

The professional version supports batch processing, allowing simultaneous conversion of multiple audio files. It supports folder uploads, automatically maintains file structure, and supports export in various text formats.

Our speech recognition engine, based on the latest AI technology, achieves over 98% accuracy for clear recordings. Even with background noise or multi-speaker scenarios, it maintains over 90% accuracy. The system continuously learns and optimizes, with accuracy improving over time.

We currently support 12 major languages, including Chinese (Mandarin, Cantonese, Min Nan), English (American, British), Japanese, Korean, French, German, Spanish, Italian, Russian, and more. The professional version also supports dialect recognition and mixed-language recognition.

Yes, we provide a complete REST API for seamless integration with your systems. The API supports batch conversion, custom vocabulary, real-time transcription, and other advanced features. We provide detailed API documentation, SDKs in multiple programming languages, and technical support.

We offer a variety of high-quality voices, including male and female voices in different languages. Each voice is professionally tuned for natural sound and expressive intonation. Speech rate and pitch can be customized to your preferences.