FAQ from SpeechEvalPro
What is SpeechEvalPro?
SpeechEvalPro is a pronunciation assessment and scoring API solution that offers high-quality, multi-dimensional Chinese and English pronunciation evaluation. It combines voice evaluation, speech recognition, and other core technologies to provide accurate and reliable pronunciation assessment for educational purposes.
How to use SpeechEvalPro?
To use SpeechEvalPro, you need to sign up for a free trial or choose a suitable pricing plan. Once you have access, you can integrate the API into your learning product or application by making HTTP or WebSocket requests. The API accepts audio files in recommended formats and supports various question types, such as phoneme, word, sentence, and chapter modes. You can refer to the documentation for detailed instructions and guidelines on API usage.
Is there an SDK available for SpeechEvalPro?
Not available for the time being. You can directly call WebAPI, which offers streaming capabilities and is lightweight and cross-platform.
What audio formats are supported for pronunciation evaluation?
It is recommended to send audio files in 16-bit sample size, 16K sample rate, 1 channel opus_raw, pcm, wav, or mp3 format. Other formats may affect scoring results.
What question types are supported, and what are the time and text length restrictions?
SpeechEvalPro supports phoneme, word, sentence, and chapter (paragraph) modes. The time and text length restrictions vary for different modes. In phoneme & word mode, the duration is up to 20 seconds. In sentence mode, the duration is up to 40 seconds, and the text length should be less than 300 characters. In chapter mode, the duration is up to 300 seconds, and the text length should be less than 10,000 characters. Please refer to the documentation for specific details.