Skip to content
VarinDocs
EN

Voice Mode

Voice mode lets you dictate messages and have replies read back to you. Turn it on at Settings → Varin → Voice.

Reading replies aloud (text-to-speech)

Section titled “Reading replies aloud (text-to-speech)”

Pick how replies are spoken:

  • browser — your browser’s built-in voices, no setup
  • OpenAI — OpenAI’s voices; paste your API key and pick a voice
  • OpenAI-compatible — any service that speaks the OpenAI format; enter its URL and, if it needs one, an API key
  • macOS say — the built-in say command, on Macs that have it

Once on, you get a play button on messages to hear them read aloud.

Dictating messages (speech-to-text)

Section titled “Dictating messages (speech-to-text)”

Pick how your speech is transcribed:

  • Local — Speech models run on the connected Varin host and download on demand. Transcription then works offline.
  • server — an OpenAI-compatible transcription service; enter its URL and, if needed, an API key

Whisper large-v3 Turbo covers 100 languages; Qwen3-ASR 0.6B covers 30; SenseVoice Small covers Chinese, English, Japanese, Korean and Cantonese; Parakeet v3 covers 25 European languages. The settings show each model’s language coverage and download size. Select a recognition language or automatic detection.

A note for phones

Section titled “A note for phones”

For reading replies aloud on a phone, the OpenAI or OpenAI-compatible options are the most reliable — mobile browsers limit the built-in voices.

Section titled “Related”