Continuous Stream Transcription provides real-time, self-service speech-to-text
Also called STT, this process converts spoken language to text. transcription. It's for use when you need audio transcription sent in a continuous stream throughout a conversation. It's ideal for use with agent assist applications.
Continuous Stream Transcription transcribes a conversation as it happens, sending the transcription in real time to the destination application. It appears in the destination application with only a minimal delay through the conversation. This allows the transcription to be available for use almost instantly. For example, if the transcription is displayed in the agent application, agents can use it to confirm details with the contact, such as an address or account number.
CXone supports another type of transcription. Turn-by-Turn Transcription provides real-time transcription that's sent in segments based on turns in the conversation.
Provider Options for Continuous Stream Transcription
Continuous Stream Transcription supports the following transcription services and languages:
- CXone CXone Transcription: Currently, this option supports:
- North American English
- International English
- Deepgram Transcription: Available languages differ by model
. - Google Transcription: Available in all languages that Google Transcription Service supports.
- Microsoft Transcription: To use this option, you must have an Azure subscription with speech service enabled. You must also have access to the Azure portal. Microsoft Transcription is available in all languages that Azure speech service supports .
Check with your transcription service provider to find out what regions the service supports.
Use Continuous Stream Transcription
You can use Continuous Stream Transcription to:
- Provide real-time transcripts for human agents, such as with SalesForce Assist.
- Provide summaries of interactions for human agents, such as with CXone AutoSummary.
- Transcribe voicemail messages. This option can be set up with custom scripting.
- Transcribe contact utterances State that allows an agent to complete work requirements after finishing an interaction for voice virtual agents that use the Voicebot Gateway.
For any application of Continuous Stream Transcription, you must create a transcription profile in Transcription Hub. The profile specifies which transcription service to use and the language to transcribe. To transcribe multiple languages, you must create a profile for each language. However, only one language can be transcribed at a time. You cannot have multiple instances of the Continuous Transcription action running at the same time.
For some transcription providers, you can configure other options to customize the transcription results. Additionally, you must use the Continuous Transcription Studio action in your scripts.