{ "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-31", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "tool": { "slug": "audio8-tts-realistic-0-6b", "name": "Audio8-TTS-Realistic 0.6B", "vendor": "Edge0", "vendorUrl": "https://edge0.ai", "kind": "weights", "category": "text-to-speech", "summary": "Audio8-TTS-Realistic 0.6B is Edge0's open-weight text-to-speech model for 23 languages, a 0.6B dual-autoregressive model with a bundled 44.1 kHz codec that speaks with or without a reference voice cloned from one clip and its transcript.", "url": "https://www.anchorterminal.com/tools/audio8-tts-realistic-0-6b", "markdownUrl": "https://www.anchorterminal.com/tools/audio8-tts-realistic-0-6b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/audio8-tts-realistic-0-6b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/audio8-tts-realistic-0-6b.json", "repo": "https://huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "Edge0/Audio8-TTS-Realistic-0.6b" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository isn't gated (checked 2026-10-30). The inference, fine-tuning and SGLang Omni adapter code is public at github.com/Edge0-AI/Audio8_TTS.", "pricing": "free", "pricingNotes": "Free to download under Apache 2.0 for the code and the weights, by the card and the LICENSE file in both repositories. Running it costs the hardware, 2.57 GB of files (BF16 safetensors plus a pickled codec), on a CUDA GPU as the card recommends. Edge0 runs no paid API for it; the Hugging Face Playground runs on ZeroGPU with a daily allowance (checked 2026-10-30).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://github.com/Edge0-AI/Audio8_TTS", "capabilities": [ "speech.tts", "speech.languages", "speech.streaming", "voice.clone", "model.open-weights" ], "tags": [ "open-weights", "model", "text-to-speech", "voice-cloning", "multilingual", "dual-ar", "custom-code", "safetensors", "self-hosted" ], "lastRelease": "2026-10-27", "graded": true, "anchor": { "graded": true, "score": 51.5, "grade": "D", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1239, "categoryRank": 18, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 60, "reach": 55, "risk": 40, "upkeep": 57 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "capability", "name": "Capability", "weight": 35, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending for this listing. Nobody independent has published results for it in at least two areas yet, so its weight is shared across the other four and the total is capped at 61 until they do or our own runs start." }, { "key": "reach", "name": "Reach", "weight": 25, "effectiveWeight": 38.46, "score": 55, "points": 21.15, "reason": "Memory earns the full 30, since the BF16 files with the codec come to 2.57 GB, about 3.1 GB with the fifth added. Runtimes score 0, because it loads only through Transformers with Edge0's remote code and Edge0's SGLang Omni plugin, not through any of the six named runtimes' own code. Builds score 0, with no quantised Realistic build from Edge0. Terms earn 15 for Apache 2.0 with nothing added, and the ungated repository gives download the full 10. Hosted too scores 0, with no provider or Edge0 API.", "checked": "2026-10-30" }, { "key": "risk", "name": "Risk", "weight": 20, "effectiveWeight": 30.77, "score": 40, "points": 12.31, "reason": "File safety gets 5, safetensors weights but a pickled codec beside them, and loading through trust_remote_code. Provenance gets 15 for files in Edge0's own organisation with hashes for every file. Licence risk keeps 15 for plain Apache 2.0. Agent guidance gets 5 for the card's request to get permission before cloning. Safety evaluation and a security programme score 0.", "checked": "2026-10-30" }, { "key": "interface", "name": "Agent interface", "weight": 10, "effectiveWeight": 15.38, "score": 60, "points": 9.23, "reason": "Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. Edge0 documents the processor inputs, the waveform output and the speech service's request fields (25). One voice and one reference per utterance gives the one-at-a-time band (10). The service documents wav, pcm and codec-code formats and opt-in streaming (15). The chat template scores 10 because the prompt is built in code. Reasoning control and context score 0, with nothing to control and a 2,048-position context.", "checked": "2026-10-30" }, { "key": "upkeep", "name": "Documentation and upkeep", "weight": 10, "effectiveWeight": 15.38, "score": 57, "points": 8.77, "reason": "The card covers everything but a knowledge cut-off (17). Training data is named in the report without sizes or a cut-off (5). The files date from 14 October 2026 (20). Nobody has opened a discussion on Hugging Face and GitHub issues couldn't be counted (0). It's a first release, with Preview kept in its own repository and no dated note (5), and the files agree with the card (10).", "checked": "2026-10-30" } ], "assessment": { "date": "2026-10-30", "basis": "public evidence", "confidence": "low", "notes": { "capability": "Pending for this listing. Independent results were found in 0 areas (none), and Capability needs 1. Its weight is shared across the other four categories and the total is capped at 61 until there are more, or our own runs start.", "interface": "Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. Edge0 documents the processor inputs, the waveform output and the speech service's request fields (25). One voice and one reference per utterance gives the one-at-a-time band (10). The service documents wav, pcm and codec-code formats and opt-in streaming (15). The chat template scores 10 because the prompt is built in code. Reasoning control and context score 0, with nothing to control and a 2,048-position context.", "reach": "Memory earns the full 30, since the BF16 files with the codec come to 2.57 GB, about 3.1 GB with the fifth added. Runtimes score 0, because it loads only through Transformers with Edge0's remote code and Edge0's SGLang Omni plugin, not through any of the six named runtimes' own code. Builds score 0, with no quantised Realistic build from Edge0. Terms earn 15 for Apache 2.0 with nothing added, and the ungated repository gives download the full 10. Hosted too scores 0, with no provider or Edge0 API.", "risk": "File safety gets 5, safetensors weights but a pickled codec beside them, and loading through trust_remote_code. Provenance gets 15 for files in Edge0's own organisation with hashes for every file. Licence risk keeps 15 for plain Apache 2.0. Agent guidance gets 5 for the card's request to get permission before cloning. Safety evaluation and a security programme score 0.", "upkeep": "The card covers everything but a knowledge cut-off (17). Training data is named in the report without sizes or a cut-off (5). The files date from 14 October 2026 (20). Nobody has opened a discussion on Hugging Face and GitHub issues couldn't be counted (0). It's a first release, with Preview kept in its own repository and no dated note (5), and the files agree with the card (10)." }, "sources": [ { "what": "model card", "url": "https://huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b", "seen": "2026-10-30" }, { "what": "gating, downloads, parameter count, base_model, empty inference provider mapping", "url": "https://huggingface.co/api/models/Edge0/Audio8-TTS-Realistic-0.6b", "seen": "2026-10-30" }, { "what": "files, sizes and hashes, and the tree at the 14 October commits", "url": "https://huggingface.co/api/models/Edge0/Audio8-TTS-Realistic-0.6b/tree/main?recursive=true", "seen": "2026-10-30" }, { "what": "8 commits, 14 to 27 October 2026", "url": "https://huggingface.co/api/models/Edge0/Audio8-TTS-Realistic-0.6b/commits/main", "seen": "2026-10-30" }, { "what": "no discussions", "url": "https://huggingface.co/api/models/Edge0/Audio8-TTS-Realistic-0.6b/discussions", "seen": "2026-10-30" }, { "what": "config, 2,048 positions, codec settings, auto_map to remote code", "url": "https://huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b/raw/main/config.json", "seen": "2026-10-30" }, { "what": "remote code, codec loaded with torch.load weights_only=True", "url": "https://huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b/raw/main/modeling_arktts.py", "seen": "2026-10-30" }, { "what": "Apache License 2.0", "url": "https://huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b/raw/main/LICENSE", "seen": "2026-10-30" }, { "what": "README, guides, SGLang Omni adapter, commit log to 28 October 2026 (blobless git clone)", "url": "https://github.com/Edge0-AI/Audio8_TTS", "seen": "2026-10-30" }, { "what": "technical report, architecture, training data and stages", "url": "https://arxiv.org/html/2610.14776", "seen": "2026-10-30" }, { "what": "Edge0's site, links to the Hugging Face and GitHub organisations", "url": "https://edge0.ai/", "seen": "2026-10-30" }, { "what": "Open TTS Leaderboard version 30-10-2026, no Audio8 row", "url": "https://huggingface.co/spaces/hf-audio/open_tts_leaderboard", "seen": "2026-10-30" }, { "what": "Artificial Analysis speech arena, no Audio8 entry", "url": "https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice", "seen": "2026-10-30" }, { "what": "TTS Arena V2, 401 on 30 October 2026", "url": "https://huggingface.co/spaces/TTS-AGI/TTS-Arena-V2", "seen": "2026-10-30" }, { "what": "vLLM registry, no arktts", "url": "https://raw.githubusercontent.com/vllm-project/vllm/main/vllm/model_executor/models/registry.py", "seen": "2026-10-30" }, { "what": "llama.cpp architectures, no arktts", "url": "https://raw.githubusercontent.com/ggml-org/llama.cpp/master/src/llama-arch.cpp", "seen": "2026-10-30" }, { "what": "Ollama library, no entry (404)", "url": "https://ollama.com/library/audio8", "seen": "2026-10-30" }, { "what": "security.txt, none (404)", "url": "https://edge0.ai/.well-known/security.txt", "seen": "2026-10-30" } ], "openQuestions": [ "Capability is pending. No independent result was found on 30 October 2026, so the total is capped at 61", "The launch post's '#1 on the Hugging Face TTS Arena' couldn't be checked, because the TTS Arena V2 Space wasn't public on 30 October 2026. It stays the vendor's claim with no deduction; if the arena returns and shows another model first, the 2-point deduction for a false #1 applies", "Unchecked, GitHub issues on Edge0-AI/Audio8_TTS, since the GitHub API isn't enabled for this repository in this session; responsiveness rests on Hugging Face, where nobody has asked anything yet", "For the founder, the training data's terms. The report says the training set includes cleaned Emilia, and Emilia's card says its original set is non-commercial (CC BY-NC 4.0) while Emilia-YODAS is CC BY 4.0. OmniVoice's publisher relicensed its weights as non-commercial for that reason; Edge0 releases under Apache 2.0. The listing reads the licence as stated and doesn't judge the question", "The codec's origin isn't stated. codec.pth differs in size and hash from Fish Audio's S2 Pro and S1 mini codecs, whose licence is non-commercial, and Edge0's NOTICE credits Fish Audio only for the DualAR design", "firstReleased is 27 October 2026, the GitHub release and Playground date; the Hub repository was created privately on 14 October and the Hub doesn't say when it went public", "Edge0 names no legal entity. The report's affiliation is AutoArk, and the relation between the two names isn't stated on Edge0's site" ] }, "negative": 0, "verdict": "A small local voice-cloning cousin for 23 languages under Apache 2.0, cloning from one clip and its exact transcript. It needs about 3 GB on a CUDA GPU through Transformers with Edge0's remote code, or Edge0's SGLang Omni plugin for a speech endpoint. The main risks are remote code and a pickled codec, and no independent benchmark yet.", "bestFor": "Agents that need multilingual voice cloning on a small CUDA GPU under a permissive licence, and can accept remote code", "strengths": [ "Apache 2.0 for code and weights, ungated, with no use policy or threshold", "2.57 GB of files, about 3.1 GB in memory, 601M parameters plus the codec", "23 languages with per-language error rates published, including the weak ones", "An OpenAI-compatible /v1/audio/speech service through Edge0's SGLang Omni plugin, with wav, pcm or codec-code output and opt-in streaming", "Fine-tuning scripts and inference code in Edge0's public GitHub repository" ], "weaknesses": [ "Loads only with trust_remote_code, and the codec ships as a 1.35 GB PyTorch pickle", "Not in any released version of Transformers, vLLM, SGLang, llama.cpp, Ollama or LM Studio, and no quantised build from Edge0", "No independent benchmark result; the card's numbers are Edge0's own, and the TTS Arena claim couldn't be checked", "A 2,048-position context shared by the reference, its transcript and the text, so long passages must be split", "No safety results, watermarking or security contact, for a model that clones a voice from one clip" ], "agentNotes": [ "Pin `transformers\u003e=4.57.0,\u003c5`; Transformers 5 can produce all-zero codes with this custom code", "Load with `AutoProcessor.from_pretrained('Edge0/Audio8-TTS-Realistic-0.6b', trust_remote_code=True)` and `AutoModel.from_pretrained(..., trust_remote_code=True, dtype=torch.bfloat16)`; review the four .py files first", "Clone with `processor(text=[...], reference_audio=['ref.wav'], reference_text=['exact transcript'], return_tensors='pt')`; a transcript that doesn't match the clip lowers stability", "Decode with `model.decode_audio(output.codes)` and write at `model.config.codec_sample_rate` (44,100 Hz)", "Split long text into short utterances; reference, transcript and text share 2,048 positions", "For an HTTP endpoint, install Edge0's SGLang Omni adapter at the pinned SGLang Omni 0.1.0 and call `/v1/audio/speech`; start the server with `AUDIO8_TTS_STREAM_ENABLED=1` for streaming", "Only clone a voice you have permission to use, and disclose synthetic audio" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 51.5 } ], "editorialScores": { "interface": 60, "reach": 55, "risk": 40, "upkeep": 57 }, "provenanceScore": 61, "checked": { "categories": { "interface": "2026-10-30", "reach": "2026-10-30", "risk": "2026-10-30", "upkeep": "2026-10-30" }, "last": "2026-10-30", "oldest": "2026-10-30", "stale": false, "staleAfterDays": 90 }, "scoreHistory": [ { "date": "2026-10-30", "grade": "D", "kind": "listed", "method": "0.7", "score": 51.5 } ] }, "connect": { "install": "git clone https://github.com/Edge0-AI/Audio8_TTS.git \u0026\u0026 cd Audio8_TTS\npip install -r requirements.txt\n# voice cloning; drop the two reference flags to speak without a reference\npython audio8_tts_infer.py --model Edge0/Audio8-TTS-Realistic-0.6b --text \"Welcome to Audio8 TTS.\" --reference-audio reference.wav --reference-text \"The exact transcript of the recording.\" --output outputs/realistic.wav" }, "letme": { "capability": "https://letme.dev/speech.tts", "tool": "https://letme.dev/audio8-tts-realistic-0-6b" }, "weights": { "trainedBy": "Edge0", "builtOn": "Edge0/Audio8-TTS-Preview-0.6b (the card's base_model, fine-tuned from it; Apache 2.0), whose slow branch is Qwen2.5 0.5B by the technical report (Apache 2.0)", "params": "0.6B (601,159,424 BF16 parameters by the Hub's count, without the bundled codec)", "context": 2048, "goodFor": "Zero-shot voice cloning from one clip and its transcript, or speech without a reference, in 23 languages, on a small CUDA GPU, under Apache 2.0.", "runtimes": [], "builds": [ { "name": "Audio8-TTS-Realistic-0.6b", "url": "https://huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b", "who": "publisher", "precision": "bf16", "sizeGB": 2.57, "memoryGB": 8, "format": "safetensors", "note": "model.safetensors 1.20 GB plus the codec as codec.pth, a 1.35 GB PyTorch pickle, and the tokenizer; 2,565,567,480 bytes summed from the Hub's file list. 2.57 GB × 1.2 = 3.1 GB" } ], "run": "git clone https://github.com/Edge0-AI/Audio8_TTS.git \u0026\u0026 cd Audio8_TTS \u0026\u0026 pip install -r requirements.txt \u0026\u0026 python audio8_tts_infer.py --model Edge0/Audio8-TTS-Realistic-0.6b --text \"Welcome to Audio8 TTS.\" --output outputs/realistic.wav", "runBuild": "Audio8-TTS-Realistic-0.6b", "checked": "2026-10-30", "minMemoryGB": 8 }, "family": { "lab": "Edge0", "family": "Audio8-TTS", "url": "https://www.anchorterminal.com/open-weights/#edge0", "others": [ { "name": "Audio8-TTS-Preview-0.6b", "url": "https://huggingface.co/Edge0/Audio8-TTS-Preview-0.6b", "params": "0.6B (601,159,424 by the Hub's count, without the codec)" }, { "name": "Audio8-TTS-Preview-0.1b", "url": "https://huggingface.co/Edge0/Audio8-TTS-Preview-0.1b", "params": "0.17B (169,779,904 by the Hub's count)" } ], "olderCount": 2 }, "alsoIn": [ "voice-cloning" ], "notable": [ "813 downloads and 109 likes on Hugging Face on 30 October 2026 (https://huggingface.co/api/models/Edge0/Audio8-TTS-Realistic-0.6b)", "Fine-tuned from Edge0's own Audio8-TTS-Preview-0.6b (28 July 2026, Apache 2.0), whose slow branch is built on Qwen2.5 0.5B by the technical report. Realistic adds 12 languages to Preview's 11 and a realism-critic training stage (https://arxiv.org/abs/2610.14776)", "The card's evaluation tables (Seed-TTS 1.25% error and 0.704 SIM, CV3 nine languages 4.86%, MiniMax 24 languages 5.89%) are Edge0's own runs, and its comparison with other models mixes results from other reports with its own reevaluations. The technical report says the model leads on intelligibility, speaker similarity and naturalness. These are the publisher's claims (https://huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b)", "The launch post's claim that it is currently #1 on the Hugging Face TTS Arena couldn't be checked. On 30 October 2026 the TTS Arena V2 Space (TTS-AGI/TTS-Arena-V2) answered 401 on Hugging Face and 404 at its own host, and it no longer appears in the TTS-AGI organisation's public Spaces. The card itself only says Audio8 is taking part and has had encouraging ratings. Neither the Open TTS Leaderboard (version 30-10-2026) nor Artificial Analysis's speech arena lists any Audio8 model (https://huggingface.co/spaces/hf-audio/open_tts_leaderboard)", "The technical report says the supervised training set combines cleaned Emilia and YODAS2 with a private collection. Emilia's dataset card says the original Emilia set is for non-commercial use under CC BY-NC 4.0 and Emilia-YODAS is CC BY 4.0; the report doesn't say which part was used. Edge0 releases the weights under Apache 2.0 (https://huggingface.co/datasets/amphion/Emilia-Dataset)", "Community conversions appeared within days, GGUF for audio.cpp, MLX at 4-bit, 8-bit and BF16 from nativ-community, and an ONNX INT4 export. None is Edge0's, and Edge0's README says there is no Realistic ONNX export (https://huggingface.co/api/models?search=Audio8-TTS-Realistic)" ], "area": "voice", "details": [ { "label": "Surface graded", "value": "The open weights at huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b, read from the model card and its 8 commits, the file list and hashes, the configs, the custom Transformers code and the LICENSE, Edge0's GitHub repository (a blobless clone of Edge0-AI/Audio8_TTS with its guides and SGLang Omni adapter), the technical report (arXiv 2610.14776) and Edge0's site on 30 October 2026. Nothing was downloaded beyond those text files or run. Edge0 has no hosted API" }, { "label": "Model", "value": "A dual-autoregressive model in the style of Fish Audio S2 Pro. A 24-layer slow branch (width 896, from Qwen2.5 0.5B by the report) predicts one semantic token per audio frame, and a 4-layer fast branch fills the other nine of ten codebooks of 4,096 entries. 601,159,424 BF16 parameters by the Hub's count, without the codec. A bundled 44.1 kHz codec at about 21.5 frames a second encodes the reference and decodes the waveform. Trained in three stages, supervised fine-tuning, GRPO with WER and speaker-similarity rewards, and GRPO with a realism critic" }, { "label": "Languages", "value": "23 by the card, Arabic, Cantonese, Chinese, Dutch, English, Finnish, French, German, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swedish, Thai, Turkish and Vietnamese. The card says quality varies, and its own CV3 table gives error rates above 20% for Thai, Finnish, Vietnamese, Hindi and Arabic. Chinese and English are about 30% each of the fine-tuning data, other languages at most 3%" }, { "label": "Files", "value": "model.safetensors (1.20 GB, BF16), codec.pth (1.35 GB, a PyTorch pickle loaded with torch.load weights_only=True), tokenizer.json (12.2 MB) and the configs, 2.57 GB in all, with a SHA-256 for the three large files on the Hub. Four Python files (configuration, modeling, codec and processing) run through trust_remote_code. No chat template; the processor builds the prompt in code. The weights and code haven't changed since 14 October; later commits are card edits" }, { "label": "Licence", "value": "Apache 2.0 for the code and the weights, in the card's metadata and text and a LICENSE file in the Hugging Face and GitHub repositories, with a NOTICE crediting Fish Audio S2 Pro's DualAR design. No use policy is attached. The card asks users to get permission to clone a voice and to disclose synthetic audio. The base Preview 0.6B is Apache 2.0 and Qwen2.5-0.5B is Apache 2.0. The codec's origin isn't stated; its file differs from Fish Audio's S2 Pro and S1 mini codecs" }, { "label": "Runtimes", "value": "Hugging Face Transformers 4.57 or later and below 5 with trust_remote_code (Transformers 5 gives all-zero codes, per the deployment guide), Edge0's command-line scripts, and Edge0's SGLang Omni adapter, a plugin pinned to SGLang Omni 0.1.0 with an OpenAI-compatible /v1/audio/speech endpoint. Not a model type in released Transformers, vLLM, SGLang, llama.cpp, Ollama or LM Studio. Community conversions run it on audio.cpp and MLX" }, { "label": "Input and output", "value": "The processor takes a list of texts and, for cloning, one reference clip with its exact transcript per text; without a reference it picks a voice. generate takes sampling settings and max_new_tokens, and decode_audio returns 44.1 kHz waveforms with their lengths. Text, reference and transcript share a 2,048-position context, so long passages are split. The SGLang Omni service takes input, references, sampling settings and response_format (wav, pcm, or codec codes as codes, codec or npy), with server-sent-event streaming when the server opts in. One reference per request, no style or emotion controls, no timestamps" }, { "label": "Recommended settings", "value": "BF16 on CUDA, temperature 0.8, top_p 0.95, top_k 50 and max_new_tokens 1024 in the card's example (generation_config.json defaults to 0.7, 0.9, 50 and 512). A clean reference clip with a transcript that matches it word for word" }, { "label": "Hardware", "value": "Python 3.10 or newer and a CUDA GPU recommended; the card's code falls back to float32 on CPU. Smoke-tested on an NVIDIA H20 in BF16. No memory figure is stated; the files are 2.57 GB. Edge0's SGLang Omni figure (0.691 s warm p50, RTF 0.116 on an H20) was measured on Preview with the same architecture" }, { "label": "Training data", "value": "Cleaned Emilia and YODAS2 plus a private collection, filtered by language, duration and ASR error, by the technical report, with the share per language. No sizes in hours and no cut-off are stated, and the card describes none" } ], "provenance": { "legalEntity": "Edge0 (edge0.ai), which names no legal entity or location on its site. The technical report's authors give their affiliation as AutoArk, and commit metadata in Edge0-AI/Audio8_TTS uses an autoark.ai domain", "domain": "edge0.ai", "domainRegistered": "2026-09-02", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b/commits/main", "securityTxt": "none", "checked": "2026-10-30", "notes": [ "edge0.ai links huggingface.co/Edge0 and github.com/Edge0-AI, and the card links back to github.com/Edge0-AI/Audio8_TTS. Hugging Face shows the Edge0 organisation as not verified. The earlier Hugging Face organisation name Audio8 redirects to Edge0, and the GitHub repository's older merges came from an Audio8-AI organisation.", "Nothing is hosted, so the licence stands in for terms of service and no privacy policy is scored.", "The Hugging Face repository was created on 14 October 2026 with a commit titled as a private release; the weights and code were last changed that day. The GitHub release commit and the Playground came on 27 October 2026, the earliest dated public release found, so firstReleased is 27 October. The Hub doesn't say when the repository was made public.", "edge0.ai/.well-known/security.txt answered 404 and edge0.ai serves no robots.txt on 30 October 2026. RDAP gives the domain's registration as 2 September 2026." ], "score": 61, "checks": [ { "check": "Legal entity named", "value": "Edge0 (edge0.ai), which names no legal entity or location on its site. The technical report's authors give their affiliation as AutoArk, and commit metadata in Edge0-AI/Audio8_TTS uses an autoark.ai domain", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "edge0.ai, registered 2026-09-02 (under a year)", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the Apache-2.0 licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "People named", "value": "1 named with their role, 1 with a public profile", "points": 10, "max": 10, "state": "ok" }, { "check": "Support route", "value": "help pages, a community", "points": 5, "max": 5, "state": "ok" } ] }, "humans": { "slug": "audio8-tts-realistic-0-6b", "checked": "2026-10-30", "company": "Edge0", "people": [ { "name": "Samuel Zeng", "role": "Founder \u0026 CEO", "founder": true, "x": "https://x.com/SamuelZengML", "page": "/people/samuel-zeng/" } ], "peopleNote": "Edge0's About page names Samuel Zeng as Founder \u0026 CEO and links his X account; it names no one else. The technical report (arXiv 2610.14776) lists four authors with the affiliation AutoArk and gives no roles, so they aren't listed. Edge0's site names no legal entity or location. No first-hand page states ownership or funding. Looked at edge0.ai (home, About, Research, Contact, Careers), the Hugging Face organisation card, the GitHub repository and two web searches for Edge0 and AutoArk funding, which found no announcement tied to Edge0 by a first-hand source. Support email left out, as the brief asks for this batch.", "companySocial": { "linkedin": "https://www.linkedin.com/company/edge0/", "x": "https://x.com/Edge0_AI", "github": "https://github.com/Edge0-AI" }, "support": { "urls": [ "https://edge0.ai/contact", "https://github.com/Edge0-AI/Audio8_TTS/issues" ], "community": [ { "label": "Discord", "url": "https://discord.gg/Gmp3gdFsd3", "kind": "discord" }, { "label": "Hugging Face discussions", "url": "https://huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b/discussions", "kind": "forum" } ] }, "sources": [ "https://edge0.ai/aboutus", "https://edge0.ai/", "https://edge0.ai/contact", "https://huggingface.co/Edge0", "https://arxiv.org/abs/2610.14776" ], "ownership": { "status": "unknown", "checked": "2026-10-30", "sources": [ "https://edge0.ai/aboutus" ] } }, "pageJsonUrl": "https://www.anchorterminal.com/tools/audio8-tts-realistic-0-6b.json" } }