Give your employees a quick way to catch up on internal updates — even when they don’t have time to read. With Text-to-Speech, you can add a Listen button to most emails. When recipients click it, an AI-generated audio summary plays directly in their browser. No app downloads, no account required.
Before You Start
- The audio is an AI-generated summary of your email — not a word-for-word reading
- All recipients hear the same audio (it’s generated once when the campaign sends)
- Dynamic Content emails are not supported
- If your campaign has multiple language versions, each version gets its own audio summary
- Available on: Grow 2.0, Enterprise 2.0, and Legacy Enterprise plans
- The feature must be turned on by an Admin or Owner in your org settings before you can use it
How to Enable Text-to-Speech
First, your ContactMonkey team needs to enable access for your organization. Once that’s done, an Admin or Owner can activate it:
- Go to Settings → ContactMonkey AI
- Toggle on Text to Speech
If you don’t see this option, reach out to your ContactMonkey account team.
How to Add a Listen Button to Your Email
- Build your campaign as usual in the Email Builder
- Insert the Text to Speech content block at the top of your draft
- (Optional) Customize the text
When the campaign sends, ContactMonkey automatically generates the audio summary and links it to the button. Recipients just click and listen.
What Recipients Experience
- They receive the email as normal with a Listen button
- Clicking the button opens the audio summary in their browser — no plugin, app, or login needed
- The summary captures the key message of the email in a natural, conversational way
FAQs
Is the audio an exact read of my email?
No — it’s an AI-generated spoken summary, not a transcript. It’s designed to capture the key message in a natural, conversational way, similar to how a colleague would give you the quick version.
What voice is used?
All campaigns use George, an AI-generated voice from ElevenLabs. The voice isn’t customizable at this time.
Can I use my own voice or a branded voice?
Not currently — we may explore this in future iterations.
Does every recipient hear the same audio?
Yes. The audio is generated once when the campaign is sent, so all recipients hear the same summary.
What if the audio fails to generate?
At the moment, there isn’t a defined fallback experience yet. Your email will still send, but the behavior for handling audio-generation failures is a planned fast-follow.
Does this work with Dynamic Content campaigns?
Not yet — Text-to-Speech is currently supported for standard campaigns only. Dynamic Content support is on the roadmap.
Does it work in multiple languages?
Yes. If your campaign has multiple language versions, each version gets a separate audio summary in that language.
Does adding the Listen button affect email deliverability?
No. It’s a standard button element and won’t impact deliverability.