Azure AI Speech
Microsoft Azure Speech service for speech-to-text transcription, text-to-speech synthesis, pronunciation assessment, and speaker recognition
Three ways to use Azure AI Speech
Chat with Geni
Ask Geni to pull data, take actions, or answer questions using this integration in a conversation.
Build a workflow
Create automated workflows that trigger on events, run on a schedule, or chain multiple tools together.
Power an app
Use this integration as a data source or action layer behind a dashboard, form, or internal tool.
Supported tools
Actions your AI agents can perform with Azure AI Speech.
Authorize Custom Model Copy
Authorize another Speech resource to copy custom models into this one.
Commit Dataset Blocks
Finalize a block-based dataset upload by committing the ordered list of previously uploaded block IDs.
Copy Custom Speech Model
Copy a custom model from another Speech resource into this one using an authorization payload.
Create Batch Synthesis
Create an asynchronous long-form text-to-speech synthesis job for audio longer than 10 minutes.
Create Custom Speech Endpoint
Deploy a custom speech-to-text model to a hosted endpoint for real-time recognition.
Create Custom Speech Model
Train a new custom speech-to-text model from a base model and training datasets.
Get started automating Azure AI Speech
Ready-to-use workflows
Prompts using Azure AI Speech
A voiceover studio your content team runs without Azure access
Audition neural voices on two sentences, render the full script once you are happy, and deliver finished audio straight to a shared Drive folder.
See which help center articles have audio in every language
One grid showing every Intercom article against every language you support, so your team can spot the gaps and narrate the pages that matter first.
A searchable library of every sales call your team records
Transcribe your recorded calls once, then search every conversation your team has had and jump straight to the moment someone said it.
Turn yesterday's Zoom webinars into WordPress blog drafts
Every weekday at 7am we transcribe yesterday's webinar recordings and hand your editor a draft post, a chapter list, and ready-to-post social copy.
Log Dropbox support calls to Zendesk with Azure Speech
Every hour on weekdays, transcribe new call recordings in your Dropbox support folder and file a clean summary, sentiment, and next steps on the right Zendesk ticket.
Turn Google Drive meeting recordings into Notion notes
Every 30 minutes during work hours, transcribe new meeting audio in your Drive folder and file a clean, structured note in your Notion meetings database.
Hourly HubSpot notes from Drive sales calls with Azure Speech
Every hour, transcribe new sales call recordings from a Google Drive folder and file a clean summary, sentiment, and next steps on the right HubSpot contact.
Turn new WordPress posts into narrated MP3s in Google Drive
Every morning at 8am, narrate each freshly published WordPress article with an Azure neural voice, save the MP3 to Google Drive, and share the link in Slack.