Generate Speech (OpenAI)
Generate Speech (OpenAI)
Convert text to speech using OpenAI's API. Includes multiple voices, speed control, and real-time playback for voiceovers and accessibility.
Problems solved
- Generate spoken audio from text with OpenAI speech models
- Play or download synthesized speech in a minimal demo UI
- Wire AI SDK speech generation through a simple API route
Use cases
- Text-to-speech playgrounds
- Accessibility read-aloud prototypes
- Voiceover drafts from written copy
- OpenAI speech API onboarding demos
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Install from the preview toolbar

Copy the install command above and run it in your project — Pro patterns include a short-lived token.
- 2
Add environment variables to .env.local
OPENAI_API_KEY
- 3
Customize the agent and tool files
Adapt prompts, tools, and stop conditions for your product — Copy for AI in the toolbar helps seed that work.
- 4
Run your dev server and open the pattern route
Install dependencies if needed, then start the app and verify responses.
Environment variables
OPENAI_API_KEYGet key
Capabilities
AI SDK APIs
generateSpeechProviders
Files added
3 filesapp/page.tsxapp/layout.tsxREADME.md
Dependencies
16 totalnpm packages
10
Registry components
Critical files
lib/actions.tsServer action using AI SDK experimental_generateSpeech with OpenAI tts-1-hd model. Handles text-to-speech conversion, voice selection, and returns base64-encoded audio with rate limiting.
Requirements
- Complexity
- Beginner









