Full-Duplex Dialogue, Smarter TTS, and Cross-Species Portrait Animation

Recent Speech Full-Duplex (FDX) models are capable of engaging in naturalistic conversation by listening and speaking at the same time. Building on this foundation, recent architectures introduce internal thinking streams to enhance their intelligence. To guarantee these streams process successfully in real time, existing methods enforce a fixed decoding rate, which assumes a hardware profile capable of a specific latency. We argue this static approach is severely suboptimal. Because internal thinking is intrinsically asynchronous, an ideal FDX model should sustain real-time conversational flow while allowing each stream to decode at its own hardware-adaptive rate. Thinking streams must process as fast as the hardware allows to deliver accurate answers faster. To solve this, we propose RUBATO, a novel multistream positional encoding that assigns independent clocks to entirely decouple the streams. This structural isolation empowers the model to zero-shot interpolate across any inference decoding speed. It drastically simplifies dataset construction by requiring training on only two extreme decoding speeds while smoothly adapting to any intermediate rate during deployment. RUBATO demonstrates consistent robustness across five spoken reasoning tasks. On Spoken GSM8K, a baseline model collapses to 1.7% accuracy at interpolated speeds. Conversely, RUBATO-Full sustains 48.7% to 51.1% accuracy across all rates, leveraging faster hardware to achieve a 6.5x shorter time-to-answer with a constant time-to-first-response. This advantage holds on BIG-Bench Audio and amplifies significantly during complex full-duplex interruptions. Specifically, when a user interjects while the model is actively speaking and reasoning, RUBATO-Full achieves 40.0% to 45.1% accuracy, whereas the baseline fails completely.

Full-duplex spoken language models (FD-SLMs) support simultaneous listening and speaking, but often lag behind half-duplex spoken language models (HD-SLMs) in general capabilities. We propose Dialogue-to-Duplex (D2), a framework that converts pretrained HD-SLMs into high-capability FD-SLMs at fine temporal granularity. D2 adapts the original audio encoder to streaming through decoder-free representation distillation and learns full-duplex interaction through supervised fine-tuning. We systematically study the effects of chunk size on full-duplex interaction, general capabilities, and inference computation. We apply D2 to two distinct HD-SLM architectures, Qwen3-Omni and LLaMA-Omni 2. At a 12.5Hz update rate, Qwen3-Omni-D2 achieves 99.2% turn-taking success with 521-ms latency, 99.5% interruption success, and a state-of-the-art VoiceBench score of 70.1.

We introduce Diffuplex, a full-duplex spoken language model based on discrete diffusion that achieves an unprecedented balance between linguistic intelligence and response efficiency. With thinking mode, Diffuplex delivers 13.0 tokens per forward pass, reaching an average of 1872 tokens per second and substantially surpassing the frontier autoregressive (AR) models in decoding speed. Without thinking, Diffuplex matches the first-audio latency of existing full-duplex models while achieving markedly stronger linguistic intelligence. This capability is enabled by separating when to say from what to say at the training level, rather than compressing both into a single autoregressive timeline. During inference, Diffuplex continuously tracks the user speech through an AR interaction policy, while independently generating and refining response content through parallel diffusion. Consequently, semantic computation is no longer bounded by the perception audio frame rate, allowing intelligence and responsiveness to improve simultaneously. Taken together, these results establish a new paradigm for spoken agents that can sustain real-time dialogue while devoting parallel computation to intelligent response generation. Training code and checkpoints will be avaliable soon.

Text language models (LMs) acquire broad linguistic and factual capabilities through large-scale pretraining, while comparable capabilities remain difficult to learn from speech alone. Recent work has shown that knowledge distillation from pretrained text LMs offers a promising way to transfer their linguistic and factual capabilities to speech models. However, existing distillation approaches have largely focused on speech-input, text-output models. This idea has yet to be explored for {\it speech-to-speech} models, which operate on both speech input and speech output. In this work we introduce a speech-to-speech pretraining method that creates an internal text interface for knowledge transfer while preserving the speech-only input and output. The model first consumes speech context without its transcription, switches to text prediction, and then uses the predicted text to lead future speech generation word by word. It also provides an interface for knowledge distillation: the internal text predictions can be directly distilled from the base text LM. To the best of our knowledge, this is the first application of text LM distillation to a speech-to-speech LM. Under matched training conditions, the proposed sequence construction substantially improves the generative perplexity of spoken continuations over speech-only and interleaved speech-text models, approaching the performance of a text-leading inner-monologue model with external ASR prompt transcription. More importantly, distillation improves factual performance under both text and speech evaluation, indicating better retention of knowledge from the base text language model.

We introduce Fish Audio Drama 3, an open-source speech generation model that turns text into directed performances, built on a 35B-parameter mixture-of-experts backbone that activates 3B parameters per token. It clones voices from multiple references, follows natural-language direction, revises a take when the next turn gives a note, voices multi-character scenes, edits existing speech by infilling, and synthesizes long-form and streaming audio. Multi-turn revision, scene dubbing, editing by infilling, and streaming text input are new in Drama 3, all in one model. Drama 3 pairs the hybrid linear-attention backbone with a new codebook multi-token-prediction audio decoder that predicts the acoustic codebooks of each frame in dedicated layers that attend over the entire sequence. The model is trained with a three-stage pre-training recipe, instruction fine-tuning, and large-batch reinforcement learning whose only reward is a single learned model of human preference. Its inference engine decodes a single stream at 271 frames per second on one H200, against 177 for Fish Audio S2, although Drama 3 has more than seven times as many parameters. The model weights are available on GitHub (https://github.com/fishaudio/fish-speech) and Hugging Face (https://huggingface.co/fishaudio/drama-3), and inference is available through SGLang-Omni (https://github.com/sgl-project/sglang-omni). We highly encourage readers to visit https://fish.audio to direct their own performances.

Text-to-speech (TTS) systems are conventionally optimized for intelligibility and speaker similarity. However, neither objective captures the prosodic detail that distinguishes human performances from synthetic speech, leaving a realism gap that larger models and higher-quality data can narrow but not close. In the absence of an objective that directly targets this gap, realism remains a persistent challenge in TTS. We present Audio8-TTS, a compact 0.6B-parameter model for zero-shot voice cloning that achieves state-of-the-art performance in intelligibility and speaker similarity, with particularly strong results in perceptual naturalness. To align the training signal with human perception rather than signal-level fidelity, we construct a quality ladder from widely used open-source TTS systems and train a realism critic to assess generated speech against matched human recordings of the same sentences. An identity-erasure objective discourages the critic from relying on generator fingerprints. We train the model in three stages: multilingual supervised fine-tuning; group relative policy optimization (GRPO) with word error rate (WER) and speaker similarity (SIM) rewards; and GRPO guided by the realism critic. The final stage improves perceived prosodic naturalness and speaker similarity while preserving WER performance.

Recent video generative models have shown strong capability in synthesizing high-quality and temporally coherent videos. Yet, adapting them for controllable portrait animation remains nontrivial, as existing methods typically rely on architectural changes or extra conditioning modules, increasing complexity and reducing compatibility with pretrained models. We present CatPortrait, a simple and effective framework that enables controllable portrait animation via 3D face guidance as in-context conditioning. CatPortrait preserves the original video generation backbone and injects structured 3D facial guidance into the input space through spatial concatenation, allowing pretrained image-to-video models to animate portraits without sacrificing their pretrained priors. CatPortrait supports both video-driven and audio-driven portrait animation within a unified framework. Extensive experiments demonstrate that CatPortrait achieves competitive or superior results across both settings.

Cross-species portrait animation, which aims to animate a source portrait of species A using a driving video of species B, is particularly challenging due to substantial anatomical differences in facial structures across species. Previous works typically fine-tune human portrait animation models on animal video datasets but often suffer from driving-species leakage. To address this, we propose CrossPortrait, a novel framework for expressive cross-species portrait animation, supporting diverse scenarios including human-to-animal, animal-to-human and cross-species animal-to-animal (e.g. cat-to-dog) animation. Specifically, we decompose the portrait motion into rigid head poses and expression keypoints. To accommodate species-specific facial structures while facilitating cross-species expression alignment, we introduce a species-routed expression encoder that incorporates species-specific LoRAs into a unified expression encoder. Furthermore, we introduce expression-level adversarial domain adaptation (Ex-ADA) to suppress driving-species-specific information in the expression latents, thereby mitigating species leakage and promoting a shared expression space across species. Extensive experiments show that our method enables expressive and identity-preserving portrait animation across diverse species and outperforms other state-of-the-art approaches.