OpenMOSS/MOSS-TTS: Open-Source Speech and Sound Generation Model Family
MOSS-TTS is an open-source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It targets high-fidelity, expressive synthesis across stable long-form speech, multi-speaker dialogue, voice/character design, environmental sound effects, and real-time streaming TTS. The repository has accumulated 2,192 stars with 53 added today, indicating active community interest.
Related guides (2)
Related events (8)
Mistral Releases Voxtral TTS: 4B-Parameter Multilingual Text-to-Speech Model
Mistral AI has launched Voxtral TTS, its first text-to-speech model, built on a 4B-parameter transformer-based autoregressive flow-matching architecture derived from Ministral 3B. The model supports 9 languages with zero-shot voice adaptation from as little as 3 seconds of reference audio, achieving 70ms latency for typical inputs and a real-time factor of ~9.7x. Human evaluations claim superior naturalness compared to ElevenLabs Flash v2.5 and parity with ElevenLabs v3. The model is available via Mistral Studio and API, targeting enterprise voice agent workflows.
MOSS: Self-Evolving Agents via Source-Level Code Rewriting
MOSS is a system enabling autonomous agents to self-evolve by rewriting their own source code rather than being limited to text-mutable artifacts like prompts or skill files. The system anchors each evolution cycle to production-failure evidence, delegates code modification to an external coding-agent CLI, and verifies candidates by replaying failures in ephemeral trial workers before promoting via consent-gated container swap with rollback. On the OpenClaw benchmark, MOSS improves a four-task mean grader score from 0.25 to 0.61 in a single cycle without human intervention. The authors argue source-level adaptation is strictly more general than text-layer evolution, being Turing-complete and immune to long-context drift.
Mistral AI Releases Voxtral: Open-Weight Speech Understanding Models in 24B and 3B Sizes
Mistral AI has released Voxtral, a family of two open-weight speech understanding models (Voxtral Small at 24B and Voxtral Mini at 3B) under the Apache 2.0 license. Both models support long-form audio up to 30-40 minutes, native multilingual transcription, built-in Q&A and summarization, and function-calling directly from voice, built on the Mistral Small 3.1 language model backbone. Benchmarks show Voxtral outperforms Whisper large-v3 across all tasks and is competitive with GPT-4o mini and Gemini 2.5 Flash on audio understanding, while pricing starts at $0.001/minute via API. Models are available on Hugging Face and through Mistral's API, with a transcription-optimized variant (Voxtral Mini Transcribe) also offered.
OpenAI Introduces Next-Generation Audio Models in the API
OpenAI is releasing new audio models via its API, including an updated text-to-speech model that accepts natural-language style instructions (e.g., 'talk like a sympathetic customer service agent'). This marks the first time developers can programmatically control speaking style through prompts rather than fixed voice presets. The release targets voice agent developers seeking finer-grained customization of synthesized speech.
Open-Source Text Generation & LLM Ecosystem at Hugging Face
Hugging Face published a blog post surveying the open-source LLM ecosystem as of mid-2023, covering text generation models, tooling, and deployment patterns available on the platform. The post highlights the breadth of open-weight models and associated infrastructure for inference and fine-tuning. It serves as a reference overview of the state of open-source LLMs at that point in time.
TTS Arena: Benchmarking Text-to-Speech Models in the Wild
Hugging Face introduces TTS Arena, a community-driven evaluation platform for text-to-speech models modeled after the LLM Chatbot Arena approach. Users listen to audio samples from competing TTS systems and vote on quality, generating Elo-based rankings. The platform aims to provide a more ecologically valid benchmark than existing automated metrics, which often fail to capture human perceptual preferences. Initial results surface rankings across open and proprietary TTS models.
OpenAI Updates Audio Models That Reason, Transcribe, and Translate
OpenAI introduced three new audio models in its Realtime API: GPT-Realtime-2 (speech-to-speech with five configurable reasoning effort levels), GPT-Realtime-Translate (70+ input languages), and GPT-Realtime-Whisper (transcription). GPT-Realtime-2 operates as an end-to-end audio model including reasoning, with latency ranging from 1.12 seconds at minimal effort to 2.33 seconds at high effort. Benchmark results are mixed: it leads Scale AI's Audio MultiChallenge and Artificial Analysis Conversational Dynamics but trails Step-Audio R1.1 Realtime and Grok Voice Think Fast 1.0 on speech reasoning and agentic tasks. The configurable reasoning-latency tradeoff is positioned as a key differentiator for voice agent applications.
Speech Synthesis, Recognition, and More With SpeechT5
This Hugging Face blog post introduces SpeechT5, a unified pre-trained model for speech synthesis, recognition, and related tasks. The post covers the model's architecture and capabilities, and explains how to use it via the Hugging Face Transformers library. SpeechT5 is a Microsoft Research model that uses a shared encoder-decoder framework across multiple speech tasks.