Speech to Text | File API
Overview
Speech-to-Text File API (STT File API)
The Speech-to-Text accurately converts speech into text using an API powered by Reverie's AI technology. The solution will transcribe the speech in real-time of various Indian languages and audio formats.
The solution is a fully managed and continually trained solution, which leverages machine learning to combine knowledge of grammar, language structure, and the composition of audio and voice signals to accurately transcribe the speech.
Prerequisite
Speech Recognition Type | File Upload |
No. of Channel | 1 |
Time Limit | Audio file length should be equal or less than 300 seconds (5 minutes) |
Supporting Languages
The STT will understand regional accents, bi-lingual nature of Indians, and is dialect-agnostic. It will transcribe the audio from widely spoken Indian languages:
|
|
|
|
|
|
|
|
|
|
|
|
Note: Our Research and Development team is continuously working to enable all the leading Indian languages on the Speech-to-Text platform and strive to enhance the existing model's accuracy.
Key Features
The Speech-to-Text solution will offer robust features that help you to deliver better user experience in products through voice commands:
Real-time Transcription
The pre-recorded audio files are transcribed accurately into text format in real-time. It will decode speech with high accuracy and confidence, even from the lower-quality audio input.
Personalize Speech Model
Tailor speech recognition to transcribe domain-specific terms and boost your transcription accuracy of specific words or phrases.
Noise Resistance
The solution will decode moderate noisy audio data recorded in various environments without requiring additional noise cancellation.
Content Filtering
An obscenity filter will detect inappropriate or unprofessional content in your audio data and filter out profane words in text output.
Flexible deployment
The API is platform agnostic and will support both the deployment model:
Cloud-based deployment
On-premise deployment
Supporting Domain
| Domain Name | Description |
|---|---|
generic | The model is trained on transcribing audio files irrespective of industry type. |
bfsi | The BFSI model is specially trained to accurately transcribe the audio files related to the banking and financial terminologies |
ecomm | |
voice-search | |
alphanumeric | |
names | |
address | |
language | |
yes-no |
Last updated