Transcription Services

VoxAction needs a transcription service before hotkeys can produce text. You can use Nurgo AI or a Whisper-compatible API.

Nurgo AI

Nurgo AI is the recommended service for most users. It provides:

  • smart dictation,
  • one-step voice translation,
  • AI assisted editing and voice actions,
  • account login,
  • subscription management,
  • monthly AI credits.

To use Nurgo AI:

  1. Open Settings.
  2. Go to Transcription.
  3. Under Transcription service, choose Nurgo AI (smart transcription & editing).
  4. Click Log in or sign up.
  5. Subscribe or manage your subscription if needed.

Whisper-Compatible API

Whisper-compatible mode is for users who want to bring their own speech-to-text API key, provider, or self-hosted endpoint. It supports basic dictation.

To configure it:

  1. Open Settings.
  2. Go to Transcription.
  3. Under Transcription service, choose Whisper (basic transcription only).
  4. Enter the API endpoint.
  5. Enter your API key.
  6. Enter the Model name.
  7. Click Apply or OK.

Default values are:

API endpoint: https://api.openai.com/v1/ Model name: whisper-1

You must supply your own API key when using the default OpenAI-compatible endpoint.

Feature Comparison

Feature Nurgo AI Whisper-compatible API
Dictation Yes Yes
Personal dictionary Yes Yes
Nearby context for transcription Yes Yes
Voice translation Yes No
AI assisted editing Yes No
Subscription management in VoxAction Yes No
Bring your own endpoint No Yes

| Feature | Nurgo AI | Whisper-compatible API | | --- | --- | --- | | Dictation | Yes | Yes | | Personal dictionary | Yes | Yes | | Nearby context for transcription | Yes | Yes | | Voice translation | Yes | No | | AI assisted editing | Yes | No | | Subscription management in VoxAction | Yes | No | | Bring your own endpoint | No | Yes |

Choosing the Right Option

Choose Nurgo AI if you want the complete VoxAction experience with minimal setup.

Choose Whisper-compatible API if you already have a provider or self-hosted transcription server and only need basic voice-to-text dictation.

Provider costs, rate limits, reliability, retention, logging, and training policies depend on the API or server you choose.