#FishAudio
Fish Speech S2 : un système TTS open source entraîné sur 10 millions d'heures d'audio dans ~50 langues. Contrôle prosodique via tags en langage naturel ([laugh], [whispers]…). Meilleurs résultats que les modèles closed-source sur Seed-TTS Eval.
https://github.com/fishaudio/fish-speech
GitHub - fishaudio/fish-speech: SOTA Open Source TTS
SOTA Open Source TTS. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
March 21, 2026 at 8:00 AM
🚀 Skyrocketing! 🚀 (200+ new stars)

📦 fishaudio / fish-speech
⭐ 25,494 (+277)
🗒 Python

SOTA Open Source TTS
GitHub - fishaudio/fish-speech: SOTA Open Source TTS
SOTA Open Source TTS. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
March 11, 2026 at 12:06 PM
how did i end up here? well let me explain..

i’m testing out this TTS model that has voice cloning (which is pretty good imo) and told my dad to send me an audio clip under the impression that it would be used to tell bedtime stories to the kids

i needed test data..

github.com/fishaudio/fi...
GitHub - fishaudio/fish-speech: SOTA Open Source TTS
SOTA Open Source TTS. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
December 5, 2024 at 4:41 AM
- Pretrained model now open source
- Cost-effective self-hosting or cloud options

🎮 Playground: fish.audio
💻 Code: github.com/fishaudio/fi...
🎯 Demo: huggingface.co/spaces/fisha...
🏆 See our rank: huggingface.co/spaces/TTS-A...
fish.audio
December 4, 2024 at 9:04 PM
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

GitHub: github.com/fishaudio/fi...
Agent Demo: huggingface.co/spaces/fisha...
GitHub - fishaudio/fish-speech: Brand new TTS solution
Brand new TTS solution. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
November 5, 2024 at 7:30 AM
In this video, I test Fish Audio, an AI voice tool with surprisingly natural and expressive voices for voiceovers and content creation. Does it really live up to the hype?

www.youtube.com/shorts/IDNIm...

#AI #AIVoice #FishAudio #ContentCreation
May 1, 2026 at 12:24 AM
github.com/fishaudio/fi...
これもメモ
AIで音声を生成する奴
github.com
April 30, 2025 at 8:47 AM
Fish Audio S2 Pro 🔊

huggingface.co/collections/...

✨ Fine-grained prosody & emotion control
✨ Supports 80+ languages
✨ Low-latency streaming & long context inference
Fish Audio S2 - a fishaudio Collection
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
March 10, 2026 at 7:42 PM
🚀 Skyrocketing! 🚀 (200+ new stars)

📦 fishaudio / fish-speech
⭐ 15,066 (+221)
🗒 Python

SOTA Open Source TTS
GitHub - fishaudio/fish-speech: SOTA Open Source TTS
SOTA Open Source TTS. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
December 5, 2024 at 12:01 PM
OpenAudio S1-mini 🔊 a new OPEN multilingual TTS model trained on 2M+ hours of data, by FishAudio

huggingface.co/fishaudio/op...

✨ Supports 14 languages
✨ 50+ emotions & tones
✨ RLHF-optimized
✨ Special effects: laughing, crying, shouting, etc.
fishaudio/openaudio-s1-mini · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
June 5, 2025 at 8:18 AM
Fish Audio has open-sourced S2, a #texttospeech model that supports fine-grained inline control of prosody and emotion using natural-language tags like [laugh], [whispers], and [super happy]

https://github.com/fishaudio/fish-speech

#ai
GitHub - fishaudio/fish-speech: SOTA Open Source TTS
SOTA Open Source TTS. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
March 11, 2026 at 9:05 PM
October 18, 2025 at 1:15 PM
台詞は自前ねw
FishAudioっていうサイトで作ったんよ✨

リップシンクや瞼の黒ずみとか気になるとこもりもりだけど、無料でこれだけ出来るんだからもっと試してみたい✨
June 26, 2026 at 12:48 PM
🎉 Celebrating! 🎉 (500+ new stars)

📦 fishaudio / fish-speech
⭐ 3,080 (+509)
🗒 Python

Brand new TTS solution
GitHub - fishaudio/fish-speech: Brand new TTS solution
Brand new TTS solution. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
July 3, 2024 at 3:00 PM
🚀 Skyrocketing! 🚀 (200+ new stars)

📦 fishaudio / fish-speech
⭐ 16,359 (+408)
🗒 Python

SOTA Open Source TTS
GitHub - fishaudio/fish-speech: SOTA Open Source TTS
SOTA Open Source TTS. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
December 9, 2024 at 5:01 PM
fishaudio/fish-speech SOTA Open Source TTS Fish Speech English | 简体中文 | Portuguese | 日本語 | 한국어 | العربية [!IMPORTANT] License Notice This codebase and its associated mode...

Origin | Interest | Match
GitHub - fishaudio/fish-speech: SOTA Open Source TTS
SOTA Open Source TTS. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
March 14, 2026 at 2:10 AM
Bonjour et bon vendredi ! Pour bien finir la semaine de travail, voici fish-speech, une solution assez récente de Text To Speech basée sur l'IA mais supportant essentiellement l'anglais et les langues asiatiques ⬇️

github.com/fishaudio/fi...
GitHub - fishaudio/fish-speech: Brand new TTS solution
Brand new TTS solution. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
May 17, 2024 at 6:02 AM
🎉 Celebrating! 🎉 (500+ new stars)

📦 fishaudio / fish-speech
⭐ 8,141 (+610)
🗒 Python

Brand new TTS solution
GitHub - fishaudio/fish-speech: Brand new TTS solution
Brand new TTS solution. Contribute to fishaudio/fish-speech development by creating an account on GitHub.
github.com
September 12, 2024 at 7:01 PM
🎙 I cloned my voice with Fish Audio, and now I can generate new voiceovers in seconds—without recording again. It even keeps the same voice across 80+ languages.

#FishAudio #AI #VoiceAI #AITools #ContentCreator
August 3, 2026 at 12:14 PM
今日のHuggingFaceトレンド

fishaudio/openaudio-s1-mini
このリポジトリは、多言語対応のテキスト音声合成モデルOpenAudio S1を提供します。
200万時間以上の音声データで学習され、感情やトーン、特殊効果を含む表現豊かな音声合成を可能にします。
fishaudio/openaudio-s1-mini · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
June 9, 2025 at 10:19 AM
🎙️ fish.audio is redefining AI voice tech with TTS, voice cloning, and STT tools.

Free voice cloning, open-source Fish Speech 1.4, and ultra-low latency...

#fishaudio #AIVoice #VoiceCloning #TextToSpeech #SpeechRecognition #AI #TechNews #VoiceTech

Read more:

aiadoptionagency.com/fish-audio-r...
June 5, 2025 at 9:05 PM
#PR #fish_audio #fishaudio

🎙️**AI音声合成の新時代!**🎙️

数秒のサンプルで声を再現!?🗣️✨

13言語対応にも対応しています!💡
今回は実際に使用して動画にしてみましたのでご覧ください!

🔻動画はこちら🔻
youtu.be/pJpUvlBVGLw
March 20, 2025 at 11:00 AM
今日のHuggingFaceトレンド

fishaudio/s2-pro
このリポジトリは、高性能テキスト読み上げ(TTS)モデルFish Audio S2 Proに関するものです。
80以上の言語に対応し、プロソディや感情を細かく制御できます。
モデルの重み、ファインチューニングコード、SGLangベースの推論エンジンが含まれており、自然言語による指示で表現を制御できるDual-ARアーキテクチャを採用しています。
非商用利用に限定されます。
fishaudio/s2-pro · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
March 23, 2026 at 10:51 AM
今日のHuggingFaceトレンド

fishaudio/fish-speech-1.4
Fish Speech V1.4は、多言語に対応したテキスト読み上げモデルです。
700k時間の音声データで学習されており、Fish Audioでデモを試すことができます。
利用規約に同意の上、非商用目的で利用可能です。
fishaudio/fish-speech-1.4 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
September 19, 2024 at 10:15 AM