Fish Audio S1 - Expressive Voice Cloning and Text-to-Speech
by•
Fish Audio S1 is the most expressive and emotionally rich TTS model—creating lifelike voices that capture emotion, rhythm, and nuance. Clone any voice in 10 seconds, preserving accent, tone, and speaking habits with unmatched realism.
Replies
Capalyze
So excited to see a more affordable and powerful solution in the field of TTS, which is both imaginative and practical. Congratulations on the launch!
Fish Audio
@nextgennerd thank you so much Stan! Would love to have you test it and let us know what you think!
YouMind
Really impressive demo — the emotion and expressiveness feel far closer to a real human than most TTS I’ve tried. Curious: how do you handle consent and IP when cloning voices from short samples (10s)
Fish Audio
@jaredl Thanks Jared and that's a great question. We've protection system in place but it's a definitely a hard trade-off with false positives, especially when the voice samples are short. We tend to be more lenient upfront + passive bans to optimize for giving as much creative freedom as possible
Fish Audio lowers the barrier to entry for individual creators and developers.
Affordable: For many users, its biggest advantage is its price. Reports indicate that its service costs about one-sixth of ElevenLabs, making professional-grade voice cloning more affordable.
Open Source Heritage and Accessibility: The Fish Audio team has a strong open source background, having created popular projects like Bert-VITS2. They have also open-sourced a smaller model, the S1-mini, on GitHub and Hugging Face for community experimentation and contribution. I've been using it extensively for three months now and it's a very useful product, especially for voice cloning!
Fish Audio
@vampxgg You're absolutely right!
Been testing a bunch of TTS tools lately, Fish blew me away. The emotion and rhythm actually feel real, and the 10-sec voice cloning is wild. Easily the most natural output I’ve heard so far.
YouMind
Really impressive demo — the emotion and expressiveness feel far closer to a real human than most TTS I’ve tried. Curious: how do you handle consent and IP when cloning voices from short samples
@Fish Audio Hi Support,
I’ve been using your tool for a few months and really like it. However, I’m getting a message to contact support about an account issue. I emailed earlier but haven’t received a response yet. Could you please assist?
Thanks,
Chemutaimce ([@]gmail.com)
Thank you, Fish Audio Team! I really love your new S1 model very much! Keep going!
I have a suggestion: Can you add a Speech-to-Speech option? I would love to see that option appear on the Fish Audio website.
@hehe6z where do I find the promo code