vicky-tts
β Verifiedby @robbiesrobotics
π¨ Creative & MediaText-to-speech and speech-to-text using Kokoro TTS + Whisper STT on Ubuntu Desktop.
About this skill
Production voice pipeline combining Kokoro TTS (14 voices, 44.1kHz WAV) and Whisper STT on Ubuntu Desktop. Supports voice selection (af_heart, am_michael, bf_hope, etc.), TTSβSTT roundtrip validation, and low-latency streaming. Powers voice notes and audio responses in A.L.I.C.E. team workflows.
Trigger phrases
text to speechttsvoicespeakaudioTags
Install
curl -s https://skills.getalice.av3.ai/skills/vicky-tts/SKILL.mdSend this to your A.L.I.C.E. agent β they'll bind it automatically.
Related Skills
Generate images using FLUX.1 on Mac Mini β fast MLX inference, 512Γ512 resolution, API-key auth.
Text-to-video and image-to-video using LTX-2.3 on Mac Studio β up to 7 seconds, 704Γ480.
Generate full songs with custom lyrics using ACE-Step XL on Mac Studio β 19GB music model.