Using the Streaming API can provide a live speech-to-text transcription and extract follow-ups, topics, action-items, questions and intents from conversations as they unfold in real-time.
- Server-side implementation (Node.js)
The client-side implementation can be ran entirely in your browser and use's your devices microphone which you can use for real-time speech-to-text transcription. When the code is ran the user will be prompted to allow permission for the browser to use their microhpone. You can view the full code example on GitHub.
- Client-side implentation
After you run execute the code above you should receive a Coversation ID (
conversationId) in the response. A Conversation ID is the key to receiving conversational insights from any conversation. As an example, here's a simple API call which grabs the speech-to-text transcription from the conversation.
Remember to replace the
conversationId in the API call with the Conversation ID you get from the previous API call.
Here's more data you can grab with our Conversation API:
View conversation topics
Summary topics provide a quick overview of the key things that were talked about in the conversation.
View action items
An action item is a specific outcome recognized in the conversation that requires one or more people in the conversation to take a specific action, e.g. set up a meeting, share a file, complete a task, etc.
This is a category of action items with a connotation to follow-up a request or a task like sending an email or making a phone call or booking an appointment or setting up a meeting.
Don't forget to sign up as a developer for Symbl to receive your API keys!