Audio

Audio messaging enables voice-based communication through phone calls, offering interactive capabilities and personalized delivery. Recipients can interact with audio messages using their phone's keypad, making this channel ideal for surveys, notifications, and interactive campaigns.

This page covers two audio message types: pre-recorded audio files and text-to-speech conversion. We recommend reviewing the General Message Types documentation first.

Message Types

Choose between two audio message creation methods:

• Audio File: Upload and combine pre-recorded audio files
• Text to Speech: Convert written text into spoken audio using AI voice synthesis

Select your preferred method using the radio buttons below:

Audio File

Audio file messages combine multiple pre-recorded audio files into a single, cohesive message. The interface consists of two main areas:

• Library: Your collection of uploaded audio files
• Message Composer: Where you arrange selected files into your final message

Audio files are played in the order they appear in the Message Composer, creating a seamless listening experience for recipients.

Library

The Library contains all your uploaded audio files. To add new files, click the Upload Audio File button and select your desired audio file:

Each audio file in your library displays the following information:

• Checkbox: Select to add the file to your Message Composer
• File Name: The name of your audio file
• Duration: File length displayed as minutes:seconds
• Play Button: Preview the audio before adding to your message

Message Composer

The Message Composer arranges your selected audio files in the order they will be played. Use the following controls to manage your audio message:

File Management:

• Drag & Drop: Reorder files by dragging them to new positions
• Remove Files: Click the 'X' button to remove files from the composer

Preview & Export:

• Preview: Click ▶ Preview Message to listen to the complete message
• Download: Click ⇓ Download to download the combined audio file

Text to Speech

Text-to-speech converts written text into natural-sounding audio using AI voice synthesis. This option is ideal for dynamic content, announcements, and messages that need to be generated programmatically.

Content

Create your message content using the standard text editor. The text you write will be converted to speech and delivered to recipients:

Pronunciation Control

Control how specific text is pronounced using SSML (Speech Synthesis Markup Language) tags. Enclose text in the following format:

<say-as interpret-as="interpretation-type">Your Text Here</say-as>

Available Interpretation Types:

• characters: Spells out each letter individually
• cardinal: Reads numbers as cardinal numbers (113 → "one hundred thirteen")
• ordinal: Reads numbers as ordinal numbers (2 → "second")
• digits: Reads numbers as individual digits (1342 → "one three four two")
• fraction: Reads fractions (3/4 → "three quarters")
• unit: Reads measurements (7kg → "seven kilograms")
• date: Reads dates with specified format:

  <say-as interpret-as="date" format="YYYY-MM-DD">2024-01-01</say-as>

• time: Reads times with specified format:

  <say-as interpret-as="time" format="HH:mm">11:16</say-as>

• address: Reads text as an address
• expletive: Censors/bleeps the text
• telephone: Reads numbers as phone numbers

Speech Rate

Control the speaking speed using the prosody tag:

<prosody rate="speed">Your Text Here</prosody>

Available Speech Rates (fastest to slowest):

1. x-fast
2. fast
3. medium
4. slow
5. x-slow

Voice Selection

Choose from multiple voice options to match your brand and audience preferences. Select your preferred voice from the dropdown menu: