Text-to-speech

Text-to-speech uses Kokoro-82M through kokoro-mlx. It runs in process after install and does not require a local TTS server. Turn it on from the menu bar or Settings -> Voice. The first enable downloads the Kokoro voice model and uses the spaCy en_core_web_sm dictionary plus system espeak-ng.

Use it

Surface	Command
Keyboard	Select text and press `Option+T`. Press `Option+T` again, Esc, or start recording to stop.
CLI	`wh whisper "text"`
CLI with voice	`wh whisper --voice af_bella "text"`
stdin	`echo "hello" \| wh whisper`

The overlay shows generation and speaking states.

Voices

Voice	ID	Type
Heart	`af_heart`	American female
Bella	`af_bella`	American female
Nova	`af_nova`	American female
Sky	`af_sky`	American female, default
Sarah	`af_sarah`	American female
Nicole	`af_nicole`	American female
Alice	`bf_alice`	British female
Emma	`bf_emma`	British female
Adam	`am_adam`	American male
Echo	`am_echo`	American male
Eric	`am_eric`	American male
Liam	`am_liam`	American male
Daniel	`bm_daniel`	British male
George	`bm_george`	British male

Configuration

[tts]
enabled = false
provider = "kokoro"
speak_shortcut = "alt+t"

[kokoro_tts]
model = "mlx-community/Kokoro-82M-bf16"
voice = "af_sky"

The provider registry lives in src/whisper_voice/tts/__init__.py.

Start

Product

Reference

Use it

Voices

Configuration

​Use it

​Voices

​Configuration

Use it

Voices

Configuration