Introducing OpenAudio S1! 🎉. Command your AI voice actor like never before:. - 🔥 Experience unparalleled expressiveness & naturalness: Voted #1 in TTS-Arena!.- 🎯 Achieve state-of-the-art accuracy: 0.008 WER & 0.004 CER in Seed TTS Eval. - 💬 Control a spectrum of emotions via

Experience state-of-the-art TTS! 🎉 OpenAudio S1 Mini, distilled from our #1 ranked S1, is now #OpenSource. Get S1 Mini:.🐙 🤗 Explore S1: Full Story: #AI #TextToSpeech.

This Valentine's Day, let Fish Audio's AI craft a heartfelt voice message for you or someone special. 💌✨ Choose from thousands of voices or let AI bring a brand-new voice to life—one that’s never been heard before. Make your love heard: #ValentinesDay.

Create stunningly lifelike AI voices at 🎙️✨

We've completed hyperparameter optimization and scaling law analysis for our End-to-End Voice Agent! 🎯 Looking to expand our GPU capacity as we prepare to launch an AI companion accessible to everyone. Stay tuned! 🚀.

A heartfelt thank you to our exceptional team for achieving this breakthrough in open-source TTS technology. Join us: We're seeking distinguished sales professionals and engineers. Contact hr@fish.audio to shape the future of voice technology.

Example: Cross-Lingual

Example: Story Telling

Example: News

Try Fish Speech 1.5:.🎮 Playground: 💻 Code: 🎯 Demo: 🏆 See our rank: Let's revolutionize voice tech together! 🐠.

Introducing Fish Speech 1.5 🎉 - Making state-of-the-art TTS accessible to everyone!. Highlights:.- #2 ranked on TTS-Arena (as "Anonymous Sparkle").- 1M hours of multilingual training data.- 13 languages supported, including English, Chinese, Japanese & more.- <150ms latency with

🔥 Voice revolution incoming! . Be part of history by joining TTS Arena's double-blind ranking challenge. Your ears could help shape the next breakthrough in AI speech.

🎉 Double release day! Introducing Fish Agent v0.1 + Fish Speech 1.4 Tech Report! 🚀. Fish Agent brings: 🔥.• True E2E architecture - no semantic layers.• Zero-shot voice cloning.• Compact 3B params for easy dev.• Text + audio input.• Ultra-fast 200ms TTFA. 📑 Just dropped:

RT @TenFramework: Yesterday, we wrapped up a hands-on workshop at the AWS GenAI LOFT in San Francisco!. We’re thrilled that over 40 develop….

Here is another demo for Germany:. To improve your experience with dialects and accents, we suggest using your own voice as a reference recording. Our team is actively looking to work with local language experts to make the tones in generated content sound more natural.

Fish Speech 1.4: 30s clips for instant accent mimicry 🎭. 🌐 8 languages, open-source, any accent.🚀 Cutting-edge voice tech for all .🗾 Demo: Kanto vs. Kansai accents. Try now: .Code: Weights:

Excited to introduce Fish Speech 1.4 - now open-source and more powerful than ever! 🎉 Our mission is to make cutting-edge voice tech accessible to everyone. What's new:.- Trained on 700k hours of multilingual data (up from 200k).- Now supports 8 languages: English, Chinese,

Insane. Just try imagining them delivering their acceptance speech—or maybe even a "no-win" speech😂 Could be pretty interesting. Check it out here: 🗣️📷 AI-powered and ready to impress. #LLM #TextToSpeech #voiceengine #Vocoder #Transformer #AI.

Sylus just left a voice message about tonight’s plan, you might want to check it out👇. Voice generated by @FishAudio . Meet more characters here: . #LLM #texttospeech #voiceengine #vocoder #transformer #AI #MachineLearning #voicetechnology #Innovation