Set up your API keys (BYOK)
You only need an API key for the optional cloud features: cloud transcription, cloud AI enhancement and voice-to-image. Dictation and AI enhancement are built in and run on your PC. AI enhancement can also use your own AI server, such as Ollama or LM Studio.
Your requests go straight to the provider, on your own account. You pay the provider directly, and several have a free tier.
Four steps
- Pick a provider from the table below and create a free account.
- Create an API key in the provider’s console (the links go straight there).
- Paste it into VoiceWink: transcription keys on the Models page, AI enhancement and image keys on the AI Enhancement page.
- Pick the cloud model in the same place, then dictate. You can switch back to a built-in model any time.
Providers
| Provider | Used for | Get your key |
|---|---|---|
| OpenAI | Transcription · AI enhancement · Images | platform.openai.com/api-keys |
| Groq | Transcription · AI enhancement | console.groq.com/keys |
| Deepgram | Transcription | console.deepgram.com |
| ElevenLabs | Transcription | elevenlabs.io → API keys |
| Anthropic | AI enhancement | platform.claude.com → keys |
| Gemini | AI enhancement · Images | aistudio.google.com/apikey |
| Mistral | AI enhancement | console.mistral.ai/api-keys |
| OpenRouter | AI enhancement · Images | openrouter.ai/settings/keys |
| Cerebras | AI enhancement | cloud.cerebras.ai |
Good to know
- Windows keeps your keys encrypted (DPAPI) under your user profile. They are never sent to DV Studio, and settings exports and problem reports leave them out.
- Usage is billed by the provider to you directly; VoiceWink adds no markup and has no quota of its own.
- You can use built-in transcription with cloud enhancement, or choose different cloud providers for transcription and enhancement.
Stuck? support@dvstudio.app