Platform edition
OpenAI / ChatGPT for Windows
OpenAI for transcription, text processing, and text-to-speech. Transcription and speech need an API key; text processing can also use your ChatGPT login.
- Version
- 1.1.6
- Plugin ID
- com.
typewhisper. openai - Requirements
- TypeWhisper 1.1.0 or newer · Windows 10 or newer · An OpenAI API key for transcription and text-to-speech
Inside this edition
Features in this edition
- Cloud transcription with GPT Transcribe, GPT Live Transcribe, Whisper 1, and the GPT-4o transcription models
- Live text while you speak with the realtime models GPT Live Transcribe and GPT Realtime Whisper
- Transcription context, language hints, and dictionary terms for GPT Transcribe and GPT Live Transcribe
- Translation into English with Whisper 1
- Text processing with an API key or your ChatGPT login, with the models available to that account
- Text-to-speech with 13 voices and optional speech instructions
Settings in this edition
- Keep OpenAI API key as the Connection method, enter your key under API key, select Save settings, then select Check connection
- To use your ChatGPT account for text processing, switch Connection method to ChatGPT, select Save settings, then select Sign in with ChatGPT or Import existing Codex login
- Choose a Transcription model and optionally add a Transcription context; Live transcription delay applies to GPT Live Transcribe
- Optionally enter Speech instructions for tone, pace or accent; the voice for spoken feedback is chosen under Spoken feedback > Voice
- Choose a Text model, Reasoning effort, and Temperature, then select Save settings; after changing accounts, select Refresh models
Guide for this edition
Set up the add-on and verify its platform-specific capabilities with a first practical workflow.
Roles in TypeWhisper
Setup
- In TypeWhisper, open Settings > Discover plugins and install OpenAI / ChatGPT. The add-on then appears in the Settings sidebar, and its page opens. If it is already installed, open its page in the sidebar.
- On the add-on's page, review the options available in this edition.
- Keep OpenAI API key as the Connection method, enter your key under API key, select Save settings, then select Check connection
- To use your ChatGPT account for text processing, switch Connection method to ChatGPT, select Save settings, then select Sign in with ChatGPT or Import existing Codex login
- Choose a Transcription model and optionally add a Transcription context; Live transcription delay applies to GPT Live Transcribe
- Optionally enter Speech instructions for tone, pace or accent; the voice for spoken feedback is chosen under Spoken feedback > Voice
- Choose a Text model, Reasoning effort, and Temperature, then select Save settings; after changing accounts, select Refresh models
- Under Settings > Dictation, select OpenAI / ChatGPT as the Provider and choose a Model. A Dictation Only workflow can also use its own transcription model.
- In a workflow, select OpenAI as the Provider under Advanced, or choose it as the Default LLM for workflows without a provider of their own.
- Under Settings > Advanced > Spoken feedback, turn on Spoken feedback and choose a voice from OpenAI / ChatGPT under Voice.
In practice
- Transcription
- Dictate a few sentences with OpenAI / ChatGPT and check the language, model, and result before you use it for longer recordings.
- LLM
- Create a meeting-notes workflow, select OpenAI as its LLM provider, and turn a short dictation into a summary, decisions, and action items.
- Text-to-Speech
- Enable spoken feedback, select OpenAI / ChatGPT as the voice provider, and test a short sentence before adjusting speed or quality.