View Categories

🗣️ How to Convert Speech to Text with OpenAI

1 min read

You can easily convert voice messages into text using OpenAI’s Whisper model integrated into Chitchatbot.ai. This is especially useful for building voice-based chatbots across social, web, and messaging channels.


🔗 Step 1: Connect OpenAI

Before using the speech-to-text feature, make sure OpenAI is connected to your account.

  1. Log in to your Chitchatbot.ai account.
  2. Go to Settings > Integrations > OpenAI.
  3. Follow the instructions to connect your OpenAI API key.
    👉 Need help? Learn how to connect OpenAI →

🎙️ Step 2: Collect the Audio Input

You’ll first need to collect the user’s voice input using a Get User Data block:

  1. Add a Get User Data step to your flow.
  2. Set the input type to Audio.
  3. Save the audio file to a custom field (e.g., user_audio).

💡 This step allows users to send a voice message to your chatbot.

audio1 - ChitChatBot - AI Bot Building Platform

⚙️ Step 3: Convert Audio to Text Using OpenAI

Now, use the OpenAI action to transcribe the audio.

  1. Add a new step:
    Action > OpenAI > Convert Speech to Text
  2. Configure the action:
    • Input: Select the custom field where the audio was saved (e.g., user_audio)
    • Output: Choose a new custom field to save the transcription (e.g., transcribed_text)

🎧 This step uses OpenAI Whisper to transcribe the user’s voice into readable text.

audio2 - ChitChatBot - AI Bot Building Platform

💬 Step 4: Display the Transcribed Text

To show the converted text to the user:

  1. Add a Text block after the OpenAI action.
  2. Insert the output custom field (e.g., {{transcribed_text}}) into the message content.

✅ You can now display or reuse the text anywhere in your flow!


🔄 Compatible Channels

This feature works seamlessly across:

  • 🌐 Website widget
  • 📱 Social messaging platforms
  • 💬 SMS and voice-enabled bots

💡 Common Use Cases

  • Voice-to-text for support tickets or customer queries
  • Audio feedback collection
  • Voice-based data entry
  • Hands-free chatbot interactions
  • Language learning and pronunciation feedback

New inbox feature

Audio Transcription in Our Inbox — Boost Your Business Productivity!

We’ve upgraded our inbox with a powerful new feature: automatic audio transcription. Now, when you receive audio messages, their text transcription will be displayed right inside the inbox.

audio transcribe - ChitChatBot - AI Bot Building Platform

How this benefits your business:

  • Save Time: Quickly read audio content without needing to listen, helping you respond faster.
  • Improve Accessibility: Easily access and review messages in noisy environments or when audio isn’t an option.
  • Enhance Productivity: Streamline communication and reduce the chance of missing important details.
  • Better Record Keeping: Keep written transcripts for reference and compliance.