Skip to main content

Speechlytics documentation

Speechlytics turns recorded and live conversations into searchable transcripts, structured analytics, quality scores, and real-time guidance.

Use this documentation to integrate with the REST and WebSocket APIs or to understand the capabilities available in the Speechlytics product.

Choose a workflow

WorkflowUse it whenStart here
Pre-recorded speechYou already have an audio file or a downloadable recording URL.Submit your first transcription
Live speechYou need transcript segments and intelligence while a call is happening.Start a live session
Product analyticsYou want call scores, topics, sentiments, agent dashboards, and QA results.Calls and analytics
Provider integrationYou want recordings imported automatically or results written back to a CRM.Integrations

Platform capabilities

  • Batch transcription from base64 audio or a media URL
  • Mono and stereo processing with speaker-separated results where the audio supports it
  • Live transcription over WebSocket, including live events, metrics, sentiment, summaries, coaching, and translation
  • Keyword matching, topics, sentiment and emotion, summaries, call scoring, and agent intelligence
  • Custom QA questions with pass/fail results and transcript evidence
  • Sensitive-content masking for recorded and live conversations
  • FrontSpin and Aircall recording import, plus HubSpot timeline export
  • REST polling, completion WebSocket notifications, and configured webhooks for retrieving completed results

API conventions

The API uses JSON and is rooted at your deployment's base URL. Examples use https://api.example.com; replace it with the URL supplied for your environment.

Most operations require a JWT in the Authorization header:

Authorization: Bearer <token>
Content-Type: application/json

Enum values are represented in the API reference as a numeric value followed by its name, for example 2 - Processed. When sending requests, use the numeric value unless your deployment has explicitly enabled string enum input.

Next steps

  1. Authenticate and submit audio.
  2. Read the feature guide to understand account-controlled processing.
  3. Use the complete API reference for request and response schemas.
Account-controlled features

Many analytics and live-intelligence capabilities are enabled per account. A valid request can still return 403 or omit optional result sections when the corresponding feature is not enabled. Contact your Speechlytics representative to change account capabilities.