CHATGPT + AI BOX
Generate audio files inside ChatGPT
ChatGPT's voice mode talks with you, but it can't produce a finished audio file you can download and use. The AI Box connector can. Add one MCP connector in ChatGPT's settings and ChatGPT can produce voiceovers, narration and podcast audio with ElevenLabs, OpenAI TTS and more — files that land right in your conversation. No API keys, no code.
HOW IT WORKS
Live in three steps
Turn on Developer mode
In ChatGPT on the web: Settings → Apps & Connectors → Advanced settings → Developer mode (paid plans).
Create the AI Box connector
Click Create, paste the AI Box MCP URL, keep OAuth authentication, and approve the popup.
Enable it in a chat and ask
Click + in the composer, toggle AI Box on, and describe what you want to create.
THE MODELS
ChatGPT picks the tool. You pick the result.
Top voice and speech models on AI Box, available to ChatGPT the moment you connect — text-to-speech for generation, Whisper for transcription.
TRY IT
Prompts that just work
PODCAST
"Use AI Box to write me a 60-second podcast intro about sleep history and ship a finished audio file."
VOICEOVER
"Turn the product demo script we just wrote into a natural-sounding voiceover I can drop into the video."
NARRATION
"Read this blog post aloud in a calm narrator voice and give me the audio file for our site."
WHAT PEOPLE MAKE
- Podcast intros, outros and ad reads
- Voiceovers for videos ChatGPT helped script
- Narrated versions of blog posts and docs
- Audio drafts to hear how copy actually sounds
- Transcription of uploaded audio via Whisper
FAQ
Questions, answered
Can ChatGPT generate audio files?+
Not on its own — ChatGPT's voice mode is a live conversation, not a file you can download and reuse. With the AI Box MCP connector, ChatGPT can produce finished audio files using models like ElevenLabs and OpenAI TTS, directly inside your chat.
How do I make ChatGPT produce a voiceover?+
In ChatGPT on the web, enable Developer mode under Settings → Apps & Connectors → Advanced settings, then click Create and paste the AI Box MCP URL: https://mcp.aibox.ai/mcp/. Then ask ChatGPT to write your script and ship it as audio — it routes the text-to-speech call through AI Box and returns a finished file. Custom connectors require a paid ChatGPT plan.
Which voice models can ChatGPT use through AI Box?+
The voice and speech models on AI Box — including ElevenLabs voices and OpenAI TTS for generation, plus Whisper for transcription. Ask in plain English and ChatGPT picks the right tool, or name the model you want.
Where do my audio files go?+
Audio files link directly in your ChatGPT conversation, and every asset is also saved to your AI Box media storage — so nothing is lost if a chat is deleted or a tool crashes mid-run.