AI Integrations
Choose the AI and speech services you use.
Configure supported providers separately for transcription, call analysis, and text-to-speech. Use commercial services, compatible endpoints, or local speech processing where supported.
Commercial providers
Configure the provider used for each supported AI or speech service. Model discovery presents the models available from the configured provider.
OpenAI
Use OpenAI models for supported analysis tasks and transcription services.
Anthropic
Use Anthropic models for supported call-analysis and Connect AI tasks.
Use Gemini for analysis, or Google speech services for supported transcription and text-to-speech tasks.
AWS
Use Amazon Transcribe for speech-to-text and Amazon Polly for text-to-speech.
OpenAI-compatible endpoints
Point supported analysis tasks at another service that implements the compatible request and response format.
Custom & on-prem providers
For deployments that can’t use third-party clouds, Custom Speech Services lets you run any TTS or transcription engine locally and route requests to it through the same configuration surface as commercial providers.
Custom speech services
Connect a local text-to-speech or transcription executable through the supported custom-service interface.
Scoped configuration
Keep provider credentials and settings with the service that uses them.
Local processing
Use a compatible local speech engine when audio should remain inside the deployment environment.
Provider choice by service
Configure transcription, analysis, and text-to-speech independently instead of selecting one vendor for every task.
Why pluggable matters
Data location
Choose a cloud or local service that fits the customer’s data-handling requirements.
Existing provider accounts
Use supported provider credentials that the operator or customer already manages.
Service-provider economics
Choose providers and models based on the cost and capability required for each service.
Independent service choices
Use different providers for transcription, analysis, and text-to-speech when one vendor is not the best fit for all three.
What you get on top
Whichever provider(s) you wire in, the user-facing AI surface stays the same:
- Post-call summarization, sentiment, action items, QA scoring, categorization, entity extraction, and compliance checking — all in the consolidated recording detail window.
- Recording transcription with speaker turns, searchable from Reports.
- On-demand voice-message transcripts in Connect with copy-to-clipboard.
- Greeting transcription for non-TTS recordings.
- Visibility cues — call history avatar badges indicate which calls have been processed.
Configure AI for your customers.
We’ll walk through provider setup, per-service configuration, and the on-prem path for regulated workloads.