Fish Audio

Our best voice model is now free for developers. S2.1 Pro- the same TTS on our paid tier, free API, 83 languages, no hard usage cap, same endpoint you already call. Already integrated? Set model: "s2.1-pro-free" and you're on S2.1 Pro.

Create any sound effect you can imagine with Fish Audio #fishaudio #soundeffect #SFX

Fish Audio’s Speech-to-Text streamlines your workflow, turning audio into accurate transcripts so you can focus on creating. #speechtotext #STT #fishaudio

Use 'Sound Effects' on Fish Audio to design any sound you can imagine! #soundeffect #fishaudio #TTS

Turn on 'Audio Separation' and cut through the noise. Get crystal-clear audio anywhere you record. #fishaudio #audioseparation #TTS

Extract any sound from your audio using 'Audio Separation' on Fish Audio #fishaudio #audioseparaption

"$99 al mes". Eso cuesta el plan Pro de ElevenLabs para generar voz con IA. Esto lo hace gratis en tu propia máquina. Y acaba de superar a los modelos cerrados. Se llama Fish Audio S2 y ya tiene 30.000 estrellas en GitHub. Entrenado con 10 millones de horas de audio en más de 80 idiomas, hace lo que hasta ahora solo veías en herramientas de pago: → clona tu voz con una muestra de 10 a 30 segundos → controla la emoción con etiquetas como [whisper], [excited] o [angry] en cualquier punto del texto → genera diálogos con varios hablantes en una sola pasada → arranca el audio en ~100 ms, listo para apps en tiempo real Y los benchmarks lo confirman: en Seed-TTS Eval registra el menor error de todos los modelos evaluados, por delante de Qwen3-TTS, MiniMax y Seed-TTS. Funciona en español, francés, inglés y decenas de idiomas más. No necesita fonemas ni preprocesado por idioma. Open source, con el modelo de 4B parámetros disponible en HuggingFace. Repo aquí ⬇️

Turn your voice into any character you can imagine using Fish Audio’s Voice Changer #fishaudio #voicechanger #TTS

Design your original character’s voice instantly with 'Voice Design' on Fish Audio! #voicedesign #fishaudio #TTS

For this Creator Spotlight, we’re featuring Leonardo Dewa, instagram : @leonrdewa, an AI anime video creator from Indonesia known for cinematic 2D anime-style short films. His animated soccer match videos went viral across the internet during the 2026 World Cup ⚽, gaining over 30 million views and being widely reposted by major tech and AI accounts such as @Evolving_AI  and others.  Full interview blog: fish.audio/blog/creator-s… #fishaudio #creatorspotlight #aianimation

@Naaufal95 👀👀👀Try it！

@FishAudio Wait, wut? For real?

Our best voice model is now free for developers. S2.1 Pro- the same TTS on our paid tier, free API, 83 languages, no hard usage cap, same endpoint you already call. Already integrated? Set model: "s2.1-pro-free" and you're on S2.1 Pro.

@TheOneNyaga check this out 👉 youtu.be/nyl3mx-D8EQ?si…

@FishAudio Does it have VC Voice clone, ref voice to source voice?

@HsounaZ96436 Start building 👉 docs.fish.audio/overview/capab…

@FishAudio there is no s2.1-pro-free where to find it ?

@Whokn3w Our voice design is live! Check here for more info 👉 fish.audio/blog/voice-des…

@FishAudio @FishAudio Do you have plans to add voice design as well?

→ docs.fish.audio/overview/capab…

A massive thank you to everyone who showed up for our Consumer AI event, and a huge shoutout to our co-host @joinbefreed for bringing the vibes! We brought together the brilliant minds behind BeFreed, Fish Audio, Creed, and 645 Ventures for a raw, candid chat on what it actually takes to scale AI right now. More to come! #fishaudio #techweek #nytechweek

Create customized voice for your character using Voice Design on Fish Audio #voicedesign #fishaudio #TTS

Fish Audio S2.1 Pro is now on Runware 🎙️ - 80+ languages with auto language detection - Natural-language emotion & delivery cues - Multi-speaker dialogue in a single generation - Realtime streaming with ultra-low latency

Clone your voice in 30s with Fish Audio #fishaudio #voiceclone #voicecloning #TTS

Create any voice you can imagine with Voice Design on Fish Audio #fishaudio #voicedesign