Save development time and transcription costs by choosing the right transcription provider for your use case, without having to do costly integrations into each one.
Jog sits on top of the major automated speech recognition platforms including Amazon Transcribe, Watson, Google Cloud Speech, and more.
Integrate with a single transcription API and have access to a variety of ASR providers
Though end-users often complain broadly about “accuracy,” savvy developers know that the quality of a voice system’s speaker splitting accuracy (or diarisation) is usually the main factor in user satisfaction and adoption.
The Jog API understands that there are different levels of speaker splitting based on the type of audio that’s used. The API will automatically detect audio file types and choose the best method available, including:
Best for flat files such as real-world recordings from a phone or WebEx audio import
100% accuracy when when independent audio channels are available
Focus on what’s truly valuable to your use case, and let Jog.ai handle the basics.
Real-time Manual Flagging Smart Flags Interactive Transcripts
Displaying automated transcripts that look as if they were transcribed manually is no small feat. With the Jog.ai platform, you don’t have to worry about the “gotcha” aspects of automated transcription that break up transcripts into illogical chunks.
Inverse Text Normalization Punctuation Paragraph Splitting Over-talking