{"version":1,"type":"story","url":"https://digestai.news/story/edge0-releases-audio8-tts-realistic-a-0-6b-open-weight-voice-cloning-m","json":"https://digestai.news/story/edge0-releases-audio8-tts-realistic-a-0-6b-open-weight-voice-cloning-m.json","markdown":"https://digestai.news/story/edge0-releases-audio8-tts-realistic-a-0-6b-open-weight-voice-cloning-m.md","slug":"edge0-releases-audio8-tts-realistic-a-0-6b-open-weight-voice-cloning-m","headline":"Edge0 releases Audio8-TTS-Realistic, a 0.6B open-weight voice cloning model","summary":"Edge0 has released Audio8-TTS-Realistic, an open-weight text-to-speech model designed for zero-shot voice cloning. The 0.6B-parameter model supports 23 languages, adding 12 to its predecessor, and is available under the Apache 2.0 license. It requires a reference audio clip and transcript to clone a voice, with weights and code shipped together for easy deployment.\n\nThe architecture uses a dual-autoregressive design inspired by Fish Audio S2 Pro, built on a Qwen2.5 0.5B base. Edge0 reports that the model achieves a 4.86% average error rate on the CV3 benchmark across 9 languages, outperforming larger open models like Qwen3-TTS-1.7B and VoxCPM2. However, performance on lower-resource languages remains weak, with a 48.57% word error rate on Thai. The company notes that while the model is competitive, 4B-class models like Higgs TTS 3 still lead on certain benchmarks.\n\nFor developers, the model is optimized for efficiency, running on a single CUDA GPU with peak memory usage of 1.1 to 1.2 GiB on an Apple M2 CPU in INT4 format. Edge0 emphasizes that the training process includes a learned realism critic to improve naturalness beyond standard word error rate metrics. A free playground is available on Hugging Face ZeroGPU for testing.","keyPoints":["Edge0 released Audio8-TTS-Realistic, a 0.6B open-weight TTS model supporting 23 languages under Apache 2.0.","The model reports a 4.86% average error on CV3, beating Qwen3-TTS-1.7B but trailing 4B-class models.","Deployment requires a CUDA GPU or Apple M2 CPU, with peak memory usage of 1.1 to 1.2 GiB in INT4."],"whyItMatters":"This release offers a lightweight, open-weight option for multilingual voice cloning, allowing developers to deploy realistic TTS on modest hardware without proprietary API costs.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Edge0","NVIDIA","Apple","Hugging Face"],"models":["Audio8-TTS-Realistic","Qwen2.5 0.5B","Qwen3-TTS-1.7B","VoxCPM2","Higgs TTS 3","Fish Audio S2 Pro"],"people":[]},"firstPublishedAt":"2026-10-30T05:02:52Z","updatedAt":"2026-10-30T05:02:52Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Edge0 Releases Audio8-TTS-Realistic, a 0.6B Voice Cloning TTS Model","url":"https://marktechpost.com/2026/10/29/edge0-audio8-tts-realistic-0-6b-voice-cloning","publishedAt":"2026-10-30T05:02:52Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Edge0 releases Audio8-TTS-Realistic, a 0.6B open-weight voice cloning model\", 30 October 2026, https://digestai.news/story/edge0-releases-audio8-tts-realistic-a-0-6b-open-weight-voice-cloning-m","publisher":"Digest AI","title":"Edge0 releases Audio8-TTS-Realistic, a 0.6B open-weight voice cloning model","datePublished":"2026-10-30T05:02:52Z","url":"https://digestai.news/story/edge0-releases-audio8-tts-realistic-a-0-6b-open-weight-voice-cloning-m"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}