π Fish Audio S2 Pro is now on Pinokio β 1-click install
Fish Audioβs 4B-parameter text-to-speech model runs fully on your own machine.
π§ What it does
π Reads text aloud in 80+ languages. English, Japanese and Chinese sound best.
ποΈ Clones a voice from 10β30 seconds of reference audio. Save it once and reuse it any time.
π Takes direction inline. Add tags like [whisper], [laughing], [excited], [pause] or [professional broadcast tone] wherever you want the delivery to change.
π₯οΈ Comes with a web UI. Choose MP3, WAV, Opus or PCM output and adjust temperature and chunk length.
π Includes a local API at /v1/tts for your own apps and scripts.
π¬ Example
I can't believe it [laughing] you actually did it! [whisper] Don't tell anyone.
π Before you install
π» For NVIDIA GPUs, plan for around 24 GB of VRAM (RTX 3090, 4090 or 5090) and around 25 GB of free disk space. CPU, AMD ROCm on Linux and Apple Silicon also work, but run slower.
π The model is gated. Accept the terms on Hugging Face before clicking Install.
https://huggingface.co/fishaudio/s2-pro
π The model weights are for research and non-commercial use only.
π Install β Start β Generate
π Fish Audio S2 Pro is now on Pinokio β 1-click install
Fish Audioβs 4B-parameter text-to-speech model runs fully on your own machine.
π§ What it does
π Reads text aloud in 80+ languages. English, Japanese and Chinese sound best.
ποΈ Clones a voice from 10β30 seconds of reference audio. Save it once and reuse it any time.
π Takes direction inline. Add tags like [whisper], [laughing], [excited], [pause] or [professional broadcast tone] wherever you want the delivery to change.
π₯οΈ Comes with a web UI. Choose MP3, WAV, Opus or PCM output and adjust temperature and chunk length.
π Includes a local API at /v1/tts for your own apps and scripts.
π¬ Example
I can't believe it [laughing] you actually did it! [whisper] Don't tell anyone.
π Before you install
π» For NVIDIA GPUs, plan for around 24 GB of VRAM (RTX 3090, 4090 or 5090) and around 25 GB of free disk space. CPU, AMD ROCm on Linux and Apple Silicon also work, but run slower.
π The model is gated. Accept the terms on Hugging Face before clicking Install.
https://huggingface.co/fishaudio/s2-pro
π The model weights are for research and non-commercial use only.
π Install β Start β Generate