It All Starts With Accurate Automated Transcription…
Automatic speech to text has never been easier thanks to our deep learning speech recognition. Simply upload an audio file via API for automatic machine transcription. This transcript can then be used for automatic video captions, visual voicemail or richer speech analytics and predictive insights.
VoiceBase returns a fully time aligned, highly accurate transcript in TXT, WORD, RTF or SRT format. Our interactive plugin provides for easy click–n-play navigation and editing.Looking for Human Transcription?
Per Word Confidence
Automatically receive the confidence score for each word in your transcript. This feature allows for accuracy monitoring and threshold setting to automate processes.Learn More
Fully time-stamped words combined with a source URL allows a customer to surface specific terms in all of their stored recordings.Upload a file to test!
VoiceBase’s Web Player SDK provides Browser UI components that extend the capabilities of popular commercial media players.Learn More
Stereo Speaker ID
Know who said what; separate the processing of stereo files by each channel to enable speaker ID, while improving accuracy and predictive analytics.Learn More
SRT Output (Captioning)
Captions are generated automatically from ASR transcripts and can be retrieved within minutes. Use this feature to display the transcript in your video player. VoiceBase supports industry standards closed captioning formats (SRT and DFXP) that can be used with commercial video players and video delivery systems.See API docs for details
Add unique words such as pronouns, company names, product names or acronyms to specific client’s vocabulary to improve transcription accuracy and keyword spotting.Contact Us