Audio8-TTS-Realistic ofrece un modelo pequeño y de código abierto para clonación de voz que equilibra la precisión multilingüe con bajos costos de implementación, convirtiéndolo en una herramienta práctica para los desarrolladores.
Resumen generado con IA. Consulta el original para comprobar el contexto y la precisión.
Este es el extracto disponible del feed. Puede estar abreviado o en el idioma original.
Edge0 has released Audio8-TTS-Realistic, an open-weight text-to-speech model for zero-shot voice cloning. Audio8-TTS-Realistic is a 0.6B-parameter model that clones a voice from 1 reference clip and transcript. It supports 23 languages, 12 more than its predecessor. The weights and code ship under Apache 2.0. For developers, the catch is competitive multilingual accuracy at a size that is cheap to fine-tune and serve. TL;DR Size: 601M main-model parameters (codec excluded); up to 2,048 packed text/audio positions of context. Runs on: a CUDA GPU is recommended; smoke-tested on NVIDIA H20 in BF16. The paper reports 1.1 to 1.2 GiB peak memory on an Apple M2 CPU (INT4 ONNX). No Realistic ONNX export is public yet. Performance: ahead of larger open models on CV3, behind 4B-class models on MiniMax. Best: 4.86% average CV3 error across 9 languages, versus 7.73% for Qwen3-TTS-1.7B. Worst: 48.57% WER on Thai (CV3) and 31.35% CER on Cantonese (MiniMax). What is Audio8-TTS-Realistic? It is the second 0.6B release in Edge0’s Audio8 TTS family. It builds on Audio8-TTS-Preview-0.6b and keeps the same Transformers inference interface. The repository bundles the checkpoint, a 44.1 kHz neural audio codec, tokenizer, processor and custom code. It can also generate speech without a reference voice. New languages are Arabic, Finnish, Hindi, Indonesian, Malay, Norwegian, Portuguese, Russian, Swedish, Thai, Turkish and Vietnamese. How does the architecture work? The model uses a dual-autoregressive (DualAR) design inspired by Fish Audio S2 Pro. According to the technical research report, the slow branch is built on Qwen2.5 0.5B. It has 24 layers at width 896 and runs at about 21.5 frames per second. Each step predicts text tokens plus the first audio codebook. A shallow 4-layer fast branch then predicts the remaining 9 codebooks in parallel. Sequential compute therefore happens only at the frame level. How does Edge0 train for realism? The team argues that word error rate (
Una ayuda automática para ordenar, basada en fuentes, palabras clave y entidades, en una escala de 1–12. Alta: 9–12; media: 6–8; baja: 1–5. No mide urgencia, verifica noticias ni representa respaldo editorial.
Samaya Sterling supera a Claude Fable 5.1 en benchmarks financieros con una undécima parte del costo, demostrando que el entrenamiento conjunto de modelos pequeños con sus arneses puede dominar dominios específicos.
El nuevo modelo joey-1 de Baseten ofrece clasificación ultrabarata y de alta velocidad para el enrutamiento y las comprobaciones de seguridad, reduciendo significativamente los costos de las aplicaciones de IA de alto volumen.
El nuevo núcleo de Prime Intellect permite un entrenamiento eficiente de modelos MoE al incorporar una pasada hacia atrás rápida, reduciendo las horas de GPU hasta en un 55 % en comparación con los marcos estándar.