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
Product Hunt
Voice tech is getting sooo good.
Side note: I'd recommend establishing a passphrase with your family. ;)
Fish Audio
@rrhoover Thank you for the hunt, Ryan, means a lot coming from you. The world’s about to get a lot louder!!
@team That passphrase feature should be on our roadmap..
Fish Audio
@rrhoover Thanks so much for the hunt! We are so excited to see how AI voice evolves with us!
Fish Audio
Hi friends! Helena here - CEO of Fish Audio.
We’re excited to launch Fish Audio S1, the most expressive and natural TTS model on the market.
6x cheaper than elevenlabs
20K active developers
5M ARR (real ARR)
Fish Audio is the first model that can clone the nuances of human speech, including accent, timbre, and speaking habits, all while being expressive, emotional, and emphatic (with just 10 seconds of audio).
With all the AI slop going over our heads, it’s more important than ever to be human-first. We are taking the lead by making sure AI voices can capture the tiniest nuances of all the diverse voices out there. Our voices can feel, empathize, and connect.
We are so thankful to the PH community for supporting us along the way. We are giving 50% OFF to all subscriptions. Just use the promo code attached to this launch. As always, we open-sourced our S1-mini model on Github and Huggingface. Join us in testing and shaping the future of human-centered AI voice!
We’re just getting started. We’d love to hear what you think about and build with it in the comments below!
🎧 Try S1 now → https://fish.audio/
💬 Come hang out in our Discord, we’re always around.
Fish Audio
@hehe6z This is lit!
ScaryStories Live
@hehe6z Big shoutout to Fish Audio! It's affordable, ultra-fast audio processing is now integrated into our real-time AI video generation experience, making everything smoother and more responsive. Love working with you!
Fish Audio
@helen9 Thank you Helen for being the most amazing user and I can't wait for the scarystories.live launch! vip support always for yall <3
ScaryStories Live
@hehe6z Thank you Helena!!! Let's fighting together! Congrats to your team, Amazing work!
All-in-1 Coliving Guide by Elysian House
@hehe6z incredible!!!!!!
@hehe6z Hi Helena, Been trying to reach support severally (via support email) with no success. I need urgent assistance. How can I be assisted?
I've tried every TTS model out there and have landed on Fish. Congratulations Helena on publicly launching! We've been using the API for months and it's been amazing.
What stood out the most to me during testing was how natural and expressive fish sounded vs everything else. It was a lot easier than I expected to get the emotion feeling right.
Other major feature that's working exceptionally well is the voice cloning. It's enabled a whole new world of use cases that wasn't possible before.
Lastly for anyone on the fence, Fish is substantially cheaper than anything else out there. Worth a shot if just for that alone!
Fish Audio
@realkevinyang thank you so much Kevin! This means the world to us. We're so lucky to have a user like you, paying lots with almost 0 complaints 🤣 We're working hard to serve you & everyone even better.
Actually we just upgraded our infra too so ttft latency is now consistently below 500ms.
For those checking this out, Serif.ai is a cracked executive assistant. I've secretly been a user for a year now and I don't know how I'd live without it
Fish Audio
@realkevinyang Thanks so much Kevin! We are working hard to live up to your praise!
minimalist phone: creating folders
I really cannot imagine how this shakes with the world of Fiverr, where people offer their voices to dub videos.
Fish Audio
@busmark_w_nika Thanks for the comment Nika! We actively make sure our voices respect the IP of existing voice actors, and our idea is to make voice creation more accessible for new and existing creators!
minimalist phone: creating folders
@zhizdev Thanks for ensuing us :)
Fish Audio
@hehe6z @rene_lonngren We already support Spanish! thought not as well as English right now, we are looking forward to adding more Spanish support
Super Intern
Most convenient open source TTS ever!
Fish Audio
@alvis_chu Yeay!!!
Currently evaluating TTS options — the demo looks good, and we’ll compare it with ElevenLabs to see the differences.
Fish Audio
@byron_fan Thanks for the support! It means a lot to us!
Fish Audio
@byron_fan Hi Byron, glad to hear you liked the demo! Let us know how you find Fish vs. 11labs :)) super curious.
Theysaid
Fish Speech looks impressive. The voice quality and range feel really natural. I’m curious though how do you make sure the tone stays consistent when switching emotions or styles? Also, how do you handle voice rights for commercial use? Amazing progress in voice tech overall.
Fish Audio
@chrishicken Thanks for the support Chris! Making sure tone stays consistent while switching styles is mainly a result of our bigger model. We are cooking better models as we speak. For voice rights we require users to have rights of voices they clone, and we have a takedown and account strikes system similar to YouTube
Theysaid
@zhizdev Good luck :)
woww this is so good! Can I clone my own voice/famous people's voices?
Fish Audio
@kile_sway you can definitely clone your own voice. The tech lets you do a lot, for celebrities there's always cc issues to pay attention to. try it and let us know what you think!
Klariqo AI Voice Assistants
Oh wow this looks really good. Do you guys have streaming TTS support as well?
Fish Audio
@ansh_deb Yes! We support streaming in our API! Our latency to first chunk is <500ms!
Klariqo AI Voice Assistants
@zhizdev That's great. Would love to give it a test try. And that's including the emotional control I assume? That's really amazing if it is. Because v3 alpha with ElevenLabs does that, but the latency on that for real-time streaming is horrible.
Fish Audio
@ansh_deb Yes! The streaming S1 API supports emotional control. It works well for simpler emotional control, and we are working hard on the next version so it has even better control!
Fish Audio
@zhizdev @ansh_deb Thank you Ansh! Let us know how we can support :)