Fish Audio Drama 3 — Pre-Release An open-source speech generation model that turns text into directed performances. Pre-trained on several hundred billion tokens across ~80 languages and dialects, Drama 3 combines a 35B-A3B hybrid linear-attention MoE backbone (initialized from Qwen3.5) with a new codebook-MTP audio decoder and RL from a single human-preference reward model. It clones voices from…
Fish Audio S2 — Pre-Release Best text-to-speech system among both open source and closed source. Trained on 10M+ hours of audio across ~50 languages, S2 combines a Dual-AR architecture (Qwen3 backbone) with GRPO reinforcement learning alignment to produce natural, emotionally rich speech with fine-grained inline control. Technical Report · Blog · Model · Playground Model Variant Params Codec Outpu…
The last stable branch before the next model release.
Fish Speech 1.5 release, both inference and finetune are done.
Last stable release before 1.5
What's Changed Add Audio Select to WebUI by @PoTaTo-Mika in #556 Fix cache max_seq_len by @AnyaCoder in #568 docs: Docker icon is missing in zh-cn README & ja README displays that it is in English & properer expression “简体中文” by @Octopus058 in #569 docs: Corrected the wrong expressions of supported languages in README by @Octopus058 in #574 Api json format by @AnyaCoder in #588 Update v1.4 readmes…
This release includes bug fix and container optimization.
Fish Speech V1.4 is a leading TTS model trained on 700k hours of audio data in multiple languages. Supported languages: English (en) ~300k hours Chinese (zh) ~300k hours German (de) ~20k hours Japanese (ja) ~20k hours French (fr) ~20k hours Spanish (es) ~20k hours Korean (ko) ~20k hours Arabic (ar) ~20k hours Have fun :)
This is the final stable release before 1.4 release on Sep 10.
In this release, we roll-out both 1.2 pretrain and SFT model, and also support auto-reranking for stable generation.
This is the final stable release before 1.2