Models & Labs
Hugging Face launches objective Open TTS Leaderboard
Hugging Face Bloghigh confidence
Why it matters
- →Provides standardized, objective benchmarks for the fragmented open-source TTS market.
- →Enables rapid comparison of multilingual performance and voice cloning fidelity without human voting delays.
- →Highlights open-weight models that are often underrepresented in commercial API-focused leaderboards.
Hugging Face has launched the Open TTS Leaderboard, a new evaluation platform designed to standardize benchmarking for multilingual text-to-speech and voice cloning models. The leaderboard utilizes objective metrics including word error rate (WER), speaker similarity scores via WavLM embeddings, and real-time factors on H200 GPUs to rank over 8,000 open-source models. This approach addresses the scalability limitations of previous arena-style leaderboards, which relied on slow human preference voting and heavily favored commercial API providers. The platform also includes a 'Listen' tab for subjective verification and streaming latency comparisons, with evaluation scripts planned for open-source release.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Hugging Face Launches FFASR Leaderboard for ASR Models
Hugging Face Blog · June 24, 2026 · Same story
- 2OpenAI Unveils GPT-Live for Voice Interaction
OpenAI · July 8, 2026 · Background
- 3OpenAI Unveils New Voice Models for ChatGPT
TechCrunch AI · July 8, 2026 · Background
- 4Hugging Face Launches Real World VoiceEQ Benchmark
Hugging Face Blog · July 15, 2026 · Same story
- 5llama.cpp b10311 Release Enhances TTS Generation
llama.cpp Releases · August 8, 2026 · Background
- 6BreezeTTS2: Real-time local voice synthesis
Sam Witteveen · August 31, 2026 · Related
- 7Base Labs partners with Hugging Face on open-weight AI safety
TechCrunch AI · September 17, 2026 · Background
- 8Google Gemini 3.8 Flash TTS with Voice Cloning
Sam Witteveen · September 24, 2026 · Related
More from Hugging Face Blog
© Hugging Face BlogAgentsagents
ServiceNow AutoSynthData automates agent training data
ServiceNow CoreAI released AutoSynthData, a pipeline that turns enterprise agent failures into targeted training datasets. By using a stronger teacher model to identify capability gaps and generate feasible, realistic tasks, it solves the bottleneck of creating high-quality synthetic data for specific environments. The system validates every generated task against strict verifiers before adding it to the curriculum, ensuring the model learns from actual weaknesses rather than noise. This approach shifts agent training from manual curation to automated, continuous improvement loops grounded in real-world constraints.
Hugging Face Blog
© Hugging Face BlogResearchmodels
Hugging Face Olmo-core 3 scales MoE training to trillions of parameters
Hugging Face’s Olmo-core 3 rewrites the rules for open-source Mixture-of-Experts training by shifting from FSDP to DDP, keeping experts resident on GPUs to slash communication overhead. This architectural pivot yields a 2.7x throughput jump on NVIDIA B300s and enables stable training of models with over one trillion total parameters while keeping active compute fixed. By integrating MXFP8 precision and optimized routing, the framework closes the efficiency gap with proprietary stacks like Megatron-Core. Researchers now have an open, battle-tested infrastructure to build massive sparse models without relying on closed-source enterprise tools.
Hugging Face Blog
© Hugging Face BlogModels & Labsother
NVIDIA Kumo Tabular beats GBDT on benchmarks
NVIDIA has released Kumo Tabular, an open foundation model that challenges the two-decade dominance of gradient-boosted trees in enterprise data. By training exclusively on synthetic tables generated via causal models, it achieves zero-shot classification and regression without feature engineering or hyperparameter tuning. It currently tops the TabArena leaderboard, offering a significant speed advantage over competitors like LimiX-2 while maintaining state-of-the-art accuracy. This shifts tabular ML from manual pipeline construction to direct inference, fundamentally changing how structured data is processed.
Hugging Face Blog
More in Models & Labs
© The Verge AIModels & Labsother
Google launches Guided Vision in Gemini Live
Google is bringing real-time audio scene description to Android via Gemini Live, directly challenging Apple’s VoiceOver Live Recognition. This feature targets users with low vision by providing immediate audio cues and follow-up Q&A capabilities for physical objects. It integrates deeply into the accessibility ecosystem through TalkBack, moving beyond simple text reading to contextual environmental awareness. The move signals a shift toward multimodal AI as a standard utility for daily navigation rather than just a novelty.
The Verge AI
© TechCrunch AIModels & Labsagents
AWS releases open-source Strands Decider 2B
Amazon’s Strands Decider 2B joins the growing wave of decision models designed to replace heavy LLMs for simple routing tasks. Built on Qwen3.5-2B, it outputs calibrated choices with confidence scores rather than generating text, offering a cheaper, faster alternative for agentic workflows. The release signals AWS’s push into specialized agent infrastructure, aiming to solve the latency and cost bottlenecks of general-purpose models. While TypeSafe’s Jev pioneered this space, Amazon’s entry brings enterprise-grade credibility and open-source accessibility to a niche that is rapidly filling with experimental clones.
TechCrunch AI
© Sam WitteveenModels & Labsmodels
Google Announces Gemini 4 Argon with 1M Token Output
Google is pushing the boundaries of context windows with Gemini 4 Argon, a new model capable of generating up to one million tokens in a single response. This isn't just about reading long documents; it's designed for complex agentic workflows where the AI must produce extensive codebases or detailed reports without truncation. Early benchmarks suggest it aims to reclaim top-tier intelligence status against competitors like GPT-6, specifically targeting tasks that require sustained reasoning and massive output generation. The shift from 64K caps to a million-token horizon fundamentally changes how developers might architect multi-step autonomous systems.
Sam Witteveen