Enhance your language learning with our Pronunciation Assessment API. Tailored to support language learners, our API evaluates pronunciation by analyzing audio files and text strings, providing comprehensive metrics for speech quality and fluency.
The Pronunciation Assessment API (scripted) provided by SpeechSuper offers a comprehensive analysis of learners' audio recordings, providing valuable insights in the following areas:
Basic Features:
Explore advanced capabilities with SpeechSuper's Pronunciation Assessment API, complementing its fundamental features. Unleash the power of:
With SpeechSuper's Pronunciation Assessment API, you access robust tools to evaluate and refine your pronunciation skills within structured contexts. Elevate your language proficiency with precise analysis and instant feedback mechanisms.
appKey
and secretKey
.If you don't have the keys, please go to SpeechSuper, and click "Contact us" to fill in the sheet. We will get in touch with you very soon!
git clone https://github.com/speechsuper/speechsuper-api-samples.git
We have http / websocket examples in multiple coding languages. Fill in your appKey
and secretKey
:
appKey = "Insert your appKey here"
secretKey = "Insert your secretKey here"
coreType = "sent.eval.promax" // sentence evaluation
refText = "The successful warrior is the average man with laser-like focus." // reference text
audioPath = "The audio path of the spoken sentence."
audioType = "wav"
Notes on Audio: SpeechSuper supports most audio formats, such as wav, mp3, opus, ogg, and amr.
To optimize file size and enhance performance, we strongly recommend recording your audio at the following settings: Audio Attribute Suggestion Sample size 16-bit Sample rate 16Khz Channels 1 (mono) Bitrate β₯ 96kbps
The English Spontaneous Speech Assessment API (Unscripted) offered by SpeechSuper provides a comprehensive analysis of learners' audio recordings, delivering valuable insights in the following areas:
In addition to the basics, the Pro features enhance the analysis by offering detailed information such as:
With SpeechSuper's API, you can unlock a wealth of information to assess and improve your English spontaneous speech skills.
Get the appKey
and secretKey
.
If you don't have the keys, please go to SpeechSuper, and click "Contact us" to fill in the sheet. We will get in touch with you very soon!
Git clone this project to your local.
git clone https://github.com/speechsuper/speechsuper-api-samples.git
Choose the example of your interest.
We have http / websocket examples in multiple coding languages. Fill in your appKey
and secretKey
:
appKey = "Insert your appKey here"
secretKey = "Insert your secretKey here"
# CoreType for English spontaneous speech assessment
coreType = "speak.eval.pro"
# Test type, currently supporting only IELTS speaking assessment
test_type = "ielts"
# Question prompt used to score relevance of the response and penalize irrelevant responses
question_prompt = "What's your favorite food?"
# Model for transcription accuracy; use "non_native" for non-native speakers, "native" otherwise
model = "non_native"
# Penalize scores for off-topic responses (1 to penalize, 0 otherwise)
penalize_offtopic = 1
# Path to the audio file of the speech
audioPath = "The audio path of the speech."
# Type of the audio file (e.g., "wav")
audioType = "wav"
Notes on Audio: SpeechSuper supports most audio formats, such as wav, mp3, opus, ogg, and amr.
To optimize file size and enhance performance, we strongly recommend recording your audio at the following settings: Audio Attribute Suggestion Sample size 16-bit Sample rate 16Khz Channels 1 (mono) Bitrate β₯ 96kbps