ElevenLabs Text To Speech
Overview
The ElevenLabs Text To Speech workflow action allows you to instantly convert written text into lifelike voice recordings. Powered by ElevenLabs’ AI voice engine, this action helps teams add warmth and personality to automated LinkedIn messages, enabling authentic, voice-based outreach directly within CRM workflows.
Use it to create human-sounding voice messages that can be attached and delivered through LinkedIn chat.
How It Works
- Add the Action
Insert the ElevenLabs Text To Speech action into any workflow. - Enter Your Message
In the Message field, provide the text you want to be spoken.
Example:{{chatgpt.1.response}}– uses a response from a previous AI action in your workflow. - Select a Voice
Enter the Voice ID from your ElevenLabs dashboard to choose a specific voice style. - Choose a Model
Select the Model ID (for example,eleven_v3) to define which ElevenLabs model to use for voice generation. - Generate and Use
The action produces a downloadable audio file URL. Attach this file to a Send a Message action to deliver the recording via LinkedIn chat.
Action Inputs
- Message: The text you want converted into speech. Supports dynamic variables, such as
{{chatgpt.1.response}}. - Voice ID: The voice identifier from your ElevenLabs dashboard that determines the voice style used.
- Model ID: The ElevenLabs model used for generation (for example,
eleven_v3).
All three fields are required for the action to run successfully.
Returned Variables
This action returns the following data after generation:
- Audio File URL: The direct URL to the generated MP3 file.
- File Size: The size of the generated file in bytes.
- Duration: The total length of the audio in seconds.
Example Use Case
Workflow Example:
- Action 1: Generate personalized outreach text using ChatGPT.
- Action 2: Convert that text into speech using ElevenLabs Text To Speech.
- Action 3: Send the generated audio as a voice message through Send a Message.
This creates an automated yet personal follow-up message that sounds natural and engaging.
Best Practices
- Use short, conversational text for best voice quality and deliverability.
- Train ElevenLabs on your own personal voice so its authentic.
Why It Matters
This action blends automation and human connection, helping you:
- Add personality to automated outreach
- Engage prospects with a familiar, conversational tone
- Localize messaging across languages and accents