API & custom models

All questions you might have about our API and/or custom speech recognition models.

• How accurate is the speech recognition?
• Do you add timestamps?
• Is it possible to train the speech recognition on specific vocabulary?
• Are there limitations on the number of files I can upload?
• How does the software recognize different speakers and times at which they speak?
• Do you offer transcription services of pre-recorded files?
• Do you offer on-premise transcription services?
• Do you offer cloud transcription services?
• Is multi-channel transcription supported?
• Do you offer real-time transcription services?
• Can you automatically detect the language of an audio file?
• What sampling rate do I need on my audio files?
• Where can I find the API documentation?
• Which audio file formats are supported?
• Which languages are supported?
• What is the price?
• How can ASR models be customized?
• How can I get Amberscript’s API?