Platform edition
Soniox for Windows
Soniox cloud transcription with live text while you dictate, recorded audio, translation to English and text-to-speech, in the United States, European Union or Japan region.
- Version
- 1.4.0
- Plugin ID
- com.
typewhisper. soniox - Requirements
- TypeWhisper 1.1.0 or newer · Windows 10 or newer · A Soniox API key from a project in the region you select
Inside this edition
Features in this edition
- Soniox v6 for live text while you dictate and for recorded audio, with Automatic following Soniox's newest model
- Optionally stay on a model version such as v5 for both live text and recorded audio
- Dictionary terms and an optional transcription context sent to Soniox as context
- Translate recorded audio to English
- Text-to-speech with the Soniox voices, chosen under Spoken feedback > Voice
- United States, European Union or Japan region for every request, without silent fallback to another region
- Your spoken languages sent as language hints, with automatic language identification
- Provider timestamps for SRT and WebVTT export of transcribed files
- Uploaded audio and transcripts deleted from Soniox after each recorded-audio transcription
Settings in this edition
- Enter your Soniox API key and choose the Region of the Soniox project that issued it
- Select Save settings, then Check connection to test the key against that region and load its models and voices
- Keep Model on Automatic or choose a version, and add a Transcription context if it helps
- Select Refresh models to load newer models later, and choose the Speech model and Default speech voice
- Turn on Live transcription under Appearance if you want live text while you dictate
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 Soniox. 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.
- Enter your Soniox API key and choose the Region of the Soniox project that issued it
- Select Save settings, then Check connection to test the key against that region and load its models and voices
- Keep Model on Automatic or choose a version, and add a Transcription context if it helps
- Select Refresh models to load newer models later, and choose the Speech model and Default speech voice
- Turn on Live transcription under Appearance if you want live text while you dictate
- Under Settings > Dictation, select Soniox as the Provider and choose a Model. A Dictation Only workflow can also use its own transcription model.
- Under Settings > Advanced > Spoken feedback, turn on Spoken feedback and choose a voice from Soniox under Voice.
In practice
- Transcription
- Dictate a few sentences with Soniox and check the language, model, and result before you use it for longer recordings.
- Text-to-Speech
- Enable spoken feedback, select Soniox as the voice provider, and test a short sentence before adjusting speed or quality.