Last updated 08-15-2026
Category:
Reviews:
Join thousands of AI enthusiasts in the World of AI!
SpeechGPT
SpeechGPT lets you hold voice conversations in the browser using your own OpenAI API key. You type or record messages, send them through a chat interface, and hear spoken replies without installing desktop software.
Unlike hosted TTS services that bundle model costs into a subscription, SpeechGPT runs in the browser and bills you only through the OpenAI, Azure Speech Services, or Amazon Polly accounts you connect. That makes it a lightweight option for developers and language learners who already have API access and want a simple voice chat front end.
The interface supports English, Spanish, and Chinese UI labels, includes a record button for speech input, and stores session data locally in the browser. It suits developers testing voice chat flows, language learners practicing spoken prompts, and anyone who wants a minimal ChatGPT voice client on mobile or desktop.
Chat interface accepts typed messages or recorded speech input with Enter to send
Requires your OpenAI API key in settings before the app will run conversations
Optional Azure Speech Services or Amazon Polly access keys for alternate text-to-speech backends
UI available in English, Spanish, and Chinese from the in-app language selector
Shift plus Enter inserts a newline without sending the message
Runs as a web app on Vercel with no separate desktop install required
No SpeechGPT subscription; you pay only your connected OpenAI or optional speech provider usage
Simple chat UI with both keyboard and record-button input in one page
Optional hooks for Azure Speech Services and Amazon Polly when you outgrow built-in synthesis
Requires supplying and managing your own OpenAI API key before any conversation works
Homepage offers minimal documentation; about and pricing pages return 404 errors
Advanced voice features depend on third-party Azure or Polly credentials you configure separately
Is SpeechGPT free to use?
SpeechGPT charges no subscription fee on speechgpt.app. You supply your own OpenAI API key, and OpenAI usage is billed to your account. Optional Azure Speech Services or Amazon Polly keys add their own provider costs if you enable them.
What API key does SpeechGPT need?
SpeechGPT requires an OpenAI API key before you can chat. The homepage prompts you to provide the key first. For alternate speech synthesis or recognition, you can also add Azure Speech Services or Amazon Polly access keys in settings.
Can SpeechGPT use voice input?
Yes. SpeechGPT includes a Record button in the chat bar so you can speak messages instead of typing. Press Enter to send a message or Shift plus Enter to add a newline without sending.
Which languages does SpeechGPT support in the UI?
SpeechGPT exposes English, Spanish, and Chinese labels in its interface language selector on speechgpt.app. Speech output quality depends on the OpenAI or optional Azure or Polly voice you configure.
Does SpeechGPT run on mobile browsers?
SpeechGPT is a web application served from speechgpt.app, so it runs in mobile and desktop browsers without a separate app store download. You still need to enter your OpenAI API key in the browser-based settings.
Where is SpeechGPT data stored?
SpeechGPT runs entirely in your browser session on speechgpt.app. Conversation handling uses the API keys you provide, and there is no paid SpeechGPT cloud account required to store chats on the service.