Skip to main content

​
Introduction

Learn how to convert spoken audio into text inside your app. The Speech-to-Text integration allows your app to transcribe audio into written text using ElevenLabs Scribe, a powerful speech recognition system. This integration enables apps to capture voice input and convert it into accurate, readable text in real time or from recorded audio. Speech-to-text is widely used for accessibility, productivity, and voice-driven interactions.

​
What You Can Build

With Speech-to-Text enabled, your app can support features such as:
  • Voice Input – Allow users to speak instead of typing, converting their speech into text instantly.
  • Meeting Transcription – Record conversations and generate accurate transcripts.
  • Voice Commands – Enable users to control app features using spoken instructions.
  • Podcast and Audio Transcription – Convert long-form audio into readable text for summaries or content reuse.
  • Accessibility Features – Help users interact with your app using voice, improving inclusivity.

​
How It Works

When the Speech-to-Text integration is enabled, your app sends audio input to ElevenLabs Scribe, which processes the speech and returns a text transcription. Your app can:
  • Capture live voice input from users
  • Process recorded audio files
  • Convert speech into structured text
  • Use transcribed text for search, summaries, or actions
This allows you to build voice-driven experiences without needing to implement complex speech recognition systems yourself. Because transcription is handled by ElevenLabs, you can focus on how the text is used within your app.

​
Example Prompts

You can use prompts like these when building your app: Add voice input Add a voice input button to my app that transcribes what the user says using ElevenLabs Scribe. Add meeting transcription Add a meeting transcription screen to my app that records audio and returns a text summary. These prompts help you quickly implement voice-to-text functionality.

​
Common Use Cases

Developers commonly use the Speech-to-Text integration for:
  • Note-taking and productivity apps
  • Meeting assistants
  • Voice-enabled interfaces
  • Transcription tools
  • Accessibility-focused applications
This integration is especially useful when users prefer speaking over typing.

​
Best Practices

When implementing speech-to-text features, consider the following:
  • Provide clear indicators when recording is active
  • Allow users to edit transcribed text
  • Handle background noise for better accuracy
  • Break long recordings into manageable segments
  • Combine transcription with summaries for better usability