{ "data": { "a": { "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" ], "assessment": { "confidence": "low", "date": "2026-10-30" }, "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 } }, "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" ], "area": "voice", "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 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/audio8-tts-realistic-0-6b.json" }, "answer": "VieNeu-TTS v3 Turbo scores 58.5 (C) on agent readiness against Audio8-TTS-Realistic 0.6B's 51.5 (D), and leads in 3 of 4 scored categories.", "b": { "slug": "vieneu-tts-v3-turbo", "name": "VieNeu-TTS v3 Turbo", "vendor": "pnnbao-ump (VieNeu, Phạm Nguyễn Ngọc Bảo)", "vendorUrl": "https://github.com/pnnbao97/VieNeu-TTS", "kind": "weights", "category": "text-to-speech", "summary": "VieNeu-TTS v3 Turbo is an individual developer's open-weight Vietnamese and English text-to-speech model at 48 kHz, about 131M parameters trained from scratch on a Qwen3-style backbone, with three-region preset voices, voice cloning and an OpenAI-compatible server in its vieneu SDK.", "url": "https://www.anchorterminal.com/tools/vieneu-tts-v3-turbo", "markdownUrl": "https://www.anchorterminal.com/tools/vieneu-tts-v3-turbo.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vieneu-tts-v3-turbo.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vieneu-tts-v3-turbo.json", "repo": "https://huggingface.co/pnnbao-ump/VieNeu-TTS-v3-Turbo", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "pnnbao-ump/VieNeu-TTS-v3-Turbo" }, { "registry": "pypi", "name": "vieneu" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository isn't gated (checked 2026-10-21). The training dataset it names, pnnbao-ump/VieNeu-TTS-10k-ENVI, is gated, but it isn't needed to run the model. The audio codec, OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano, downloads separately and isn't gated.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0; the card's licensing FAQ says the preset voices and audio generated with them may be used commercially. Running it costs very little hardware, under 0.5 GB of files, on a CPU through ONNX Runtime or an NVIDIA GPU through PyTorch, about 1 GB of VRAM at 16 streams on an RTX 3060 per the publisher (checked 2026-10-21).", "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 2026-10-21).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-21" }, "docsUrl": "https://github.com/pnnbao97/VieNeu-TTS", "capabilities": [ "speech.tts", "speech.voices", "speech.languages", "speech.streaming", "voice.clone", "model.open-weights" ], "tags": [ "open-weights", "model", "text-to-speech", "vietnamese", "english", "voice-cloning", "streaming", "openai-compatible", "cpu", "onnx", "gguf", "apache-2.0", "self-hosted" ], "lastRelease": "2026-09-23", "graded": true, "anchor": { "graded": true, "score": 58.5, "grade": "C", "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": 10, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 60, "reach": 65, "risk": 50, "upkeep": 58 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-21" }, "negative": 0, "verdict": "A tiny, fast speech cousin for Vietnamese and English, with regional preset voices, cloning from a short clip and an OpenAI-compatible streaming endpoint, under Apache 2.0. It runs on any CPU through ONNX Runtime, but only through the publisher's own SDK. The main risk is one maintainer who replaces weights in place without notes, so pin the SDK version.", "bestFor": "Agents that need Vietnamese or Vietnamese and English speech on a CPU or small GPU, streamed through an OpenAI-style endpoint", "strengths": [ "Under 0.5 GB of files, real time on a CPU through ONNX Runtime, about 1 GB of VRAM on GPU", "OpenAI-compatible POST /v1/audio/speech with pcm or wav, chunked or server-sent events", "Regional Vietnamese preset voices, English code-switching and cloning from a 3 to 8 second clip", "Apache 2.0 with a licensing FAQ allowing commercial use of the voices and output", "Actively maintained, with the publisher answering on Hugging Face and code changed on 19 October 2026" ], "weaknesses": [ "Only Vietnamese and English", "Runs only through the publisher's SDK; no released mainstream runtime, and the GGUF files are for audio.cpp", "Weights replaced in place many times without notes, and the card lags the SDK's voice list", "One individual maintainer, with no security contact or safety results", "Training data is a gated set with an undisclosed pipeline" ], "agentNotes": [ "On CPU, `pip install vieneu`, then `from vieneu import Vieneu; tts = Vieneu(); tts.save(tts.infer(text, voice='Mai Anh'), 'out.wav')`; `Vieneu(precision='int8')` is about twice as fast on a CPU with VNNI", "On GPU, install torch 2.8 for CUDA 12.8 and transformers 4.57.6 before vieneu; it switches to PyTorch with batching and stream scheduling", "Serve with `uv run python -m apps.openai_speech` from a clone of pnnbao97/VieNeu-TTS, then POST to http://localhost:8000/v1/audio/speech with model vieneu-v3-turbo, voice and response_format pcm or wav", "Call `list_preset_voices()` for the voice names of your installed version; pin the SDK version if the roster matters", "Clone with `ref_audio='voice.wav', denoise=True`, or enrol once with `add_voice(name, path)` and reuse the name", "Keep temperature near 0.8; the style argument is ignored on v3 Turbo", "Only clone a voice you have the right to use" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58.5 } ], "editorialScores": { "interface": 60, "reach": 65, "risk": 50, "upkeep": 58 }, "provenanceScore": 61, "checked": { "categories": { "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install vieneu # CPU, torch-free ONNX path; for CUDA install torch 2.8 and transformers 4.57.6 first\npython -c \"from vieneu import Vieneu; tts = Vieneu(); tts.save(tts.infer('Xin chào, đây là VieNeu-TTS.', voice='Mai Anh'), 'out.wav')\"", "http": "# after: git clone https://github.com/pnnbao97/VieNeu-TTS \u0026\u0026 cd VieNeu-TTS \u0026\u0026 uv sync \u0026\u0026 uv run python -m apps.openai_speech\ncurl -X POST http://localhost:8000/v1/audio/speech \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\": \"vieneu-v3-turbo\", \"voice\": \"Mai Anh\", \"input\": \"Xin chào!\", \"response_format\": \"wav\"}' \\\n --output speech.wav" }, "letme": { "capability": "https://letme.dev/speech.tts", "tool": "https://letme.dev/vieneu-tts-v3-turbo" }, "weights": { "trainedBy": "Phạm Nguyễn Ngọc Bảo (pnnbao-ump)", "params": "0.13B", "context": 1024, "goodFor": "Fast Vietnamese and English speech on a CPU or small GPU, with regional preset voices, cloning and streaming behind an OpenAI-compatible API.", "runtimes": [], "builds": [ { "name": "VieNeu-TTS-v3-Turbo update/ (safetensors)", "url": "https://huggingface.co/pnnbao-ump/VieNeu-TTS-v3-Turbo/tree/main/update", "who": "publisher", "precision": "bf16", "sizeGB": 0.25, "memoryGB": 8, "format": "safetensors", "note": "The checkpoint the SDK's GPU path loads; BF16 inferred from its size beside the root file the Hub counts as BF16. Needs the 0.09 GB MOSS-Audio-Tokenizer-Nano codec, loaded with trust_remote_code" }, { "name": "VieNeu-TTS-v3-Turbo onnx_update/ (FP32)", "url": "https://huggingface.co/pnnbao-ump/VieNeu-TTS-v3-Turbo/tree/main/onnx_update", "who": "publisher", "precision": "fp32", "sizeGB": 0.48, "memoryGB": 8, "format": "onnx", "note": "The SDK's default CPU path" }, { "name": "VieNeu-TTS-v3-Turbo onnx_int8/ (INT8)", "url": "https://huggingface.co/pnnbao-ump/VieNeu-TTS-v3-Turbo/tree/main/onnx_int8", "who": "publisher", "precision": "int8", "sizeGB": 0.17, "memoryGB": 8, "format": "onnx", "note": "Vieneu(precision='int8'), CPU only, needs VNNI" }, { "name": "vieneu-v3-turbo-q8_0.gguf", "url": "https://huggingface.co/pnnbao-ump/VieNeu-TTS-v3-Turbo/blob/main/gguf/vieneu-v3-turbo-q8_0.gguf", "who": "publisher", "precision": "q8_0", "sizeGB": 0.19, "memoryGB": 8, "format": "gguf", "note": "For audio.cpp, not llama.cpp. A BF16 GGUF (0.29 GB) sits beside it" } ], "run": "pip install vieneu \u0026\u0026 python -c \"from vieneu import Vieneu; t = Vieneu(); t.save(t.infer('Xin chào!', voice='Mai Anh'), 'out.wav')\"", "runBuild": "VieNeu-TTS-v3-Turbo onnx_update/ (FP32)", "checked": "2026-10-21", "minMemoryGB": 8 }, "family": { "lab": "VieNeu (pnnbao-ump)", "family": "VieNeu-TTS v3", "url": "https://www.anchorterminal.com/open-weights/#vieneu", "others": [ { "name": "VieNeu-TTS-v3-Nano", "url": "https://huggingface.co/pnnbao-ump/VieNeu-TTS-v3-Nano", "params": "not stated (no safetensors count on the Hub)" } ], "olderCount": 7 }, "alsoIn": [ "voice-cloning" ], "area": "voice", "provenance": { "legalEntity": "Phạm Nguyễn Ngọc Bảo, an individual (named on the card as author; Hugging Face account pnnbao-ump, GitHub account pnnbao97). No company found", "domain": "", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/pnnbao97/VieNeu-TTS/commits/main", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "The card links github.com/pnnbao97/VieNeu-TTS, and that README links back to huggingface.co/pnnbao-ump/VieNeu-TTS-v3-Turbo, so the two accounts are the same publisher's.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored. There is no domain of the publisher's own.", "The Hugging Face history is 65 commits from 5 June to 23 September 2026. Many replace model.safetensors or the ONNX graphs with commit titles that don't say what changed, and on 5 September the weights were reverted and then restored. The GitHub repository is tagged up to v3.8.3 (23 September 2026) and last changed on 19 October 2026.", "The GitHub repository has no SECURITY.md (its .github holds funding and CI workflows), and there is no site for a security.txt." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vieneu-tts-v3-turbo.json", "live": { "slug": "vieneu-tts-v3-turbo", "versions": [ { "registry": "pypi", "name": "vieneu", "version": "3.8.3", "released": "2026-09-23", "seenAt": "2026-10-30T14:53:54.895034378Z" } ], "pypiWeekly": 11292, "updatedAt": "2026-10-30T14:53:54.895034378Z" } }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Edge0", "b": "pnnbao-ump (VieNeu, Phạm Nguyễn Ngọc Bảo)", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-27", "b": "2026-09-23", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "VieNeu-TTS v3 Turbo scores 58.5 (C) on agent readiness against Audio8-TTS-Realistic 0.6B's 51.5 (D), and leads in 3 of 4 scored categories.", "question": "Which is better for AI agents, Audio8-TTS-Realistic 0.6B or VieNeu-TTS v3 Turbo?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Agents that need multilingual voice cloning on a small CUDA GPU under a permissive licence, and can accept remote code", "slug": "audio8-tts-realistic-0-6b", "watchFor": "Loads only with trust_remote_code, and the codec ships as a 1.35 GB PyTorch pickle" }, { "aheadOn": [ "Reach, 65 against 55", "Risk, 50 against 40" ], "also": null, "goodFor": "Agents that need Vietnamese or Vietnamese and English speech on a CPU or small GPU, streamed through an OpenAI-style endpoint", "slug": "vieneu-tts-v3-turbo", "watchFor": "Only Vietnamese and English" } ], "job": { "capability": "speech.tts", "name": "Text-to-speech" }, "others": [ { "json": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-fish-audio-drama-3.json", "title": "Audio8-TTS-Realistic 0.6B vs Fish Audio Drama 3", "url": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-fish-audio-drama-3" }, { "json": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-fish-audio-s2-pro.json", "title": "Audio8-TTS-Realistic 0.6B vs Fish Audio S2 Pro", "url": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-fish-audio-s2-pro" }, { "json": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-ming-3-0-tts-0-5b.json", "title": "Audio8-TTS-Realistic 0.6B vs Ming-3.0-tts-0.5B", "url": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-ming-3-0-tts-0-5b" }, { "json": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-ming-3-0-tts-tiny.json", "title": "Audio8-TTS-Realistic 0.6B vs Ming-3.0-tts-tiny", "url": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-ming-3-0-tts-tiny" }, { "json": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-omnivoice.json", "title": "Audio8-TTS-Realistic 0.6B vs OmniVoice", "url": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-omnivoice" }, { "json": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-qwen3-tts-1-7b-customvoice.json", "title": "Audio8-TTS-Realistic 0.6B vs Qwen3-TTS 12Hz 1.7B CustomVoice", "url": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-qwen3-tts-1-7b-customvoice" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo.json", "title": "Fish Audio Drama 3 vs VieNeu-TTS v3 Turbo", "url": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-vieneu-tts-v3-turbo.json", "title": "Fish Audio S2 Pro vs VieNeu-TTS v3 Turbo", "url": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-vieneu-tts-v3-turbo" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-vieneu-tts-v3-turbo.json", "title": "Ming-3.0-tts-0.5B vs VieNeu-TTS v3 Turbo", "url": "https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-vieneu-tts-v3-turbo" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-tts-tiny-vs-vieneu-tts-v3-turbo.json", "title": "Ming-3.0-tts-tiny vs VieNeu-TTS v3 Turbo", "url": "https://www.anchorterminal.com/compare/ming-3-0-tts-tiny-vs-vieneu-tts-v3-turbo" }, { "json": "https://www.anchorterminal.com/compare/omnivoice-vs-vieneu-tts-v3-turbo.json", "title": "OmniVoice vs VieNeu-TTS v3 Turbo", "url": "https://www.anchorterminal.com/compare/omnivoice-vs-vieneu-tts-v3-turbo" }, { "json": "https://www.anchorterminal.com/compare/qwen3-tts-1-7b-customvoice-vs-vieneu-tts-v3-turbo.json", "title": "Qwen3-TTS 12Hz 1.7B CustomVoice vs VieNeu-TTS v3 Turbo", "url": "https://www.anchorterminal.com/compare/qwen3-tts-1-7b-customvoice-vs-vieneu-tts-v3-turbo" } ], "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "audio8-tts-realistic-0-6b": 55, "by": 10, "edge": "vieneu-tts-v3-turbo", "key": "reach", "name": "Reach", "vieneu-tts-v3-turbo": 65, "weight": 25 }, { "audio8-tts-realistic-0-6b": 40, "by": 10, "edge": "vieneu-tts-v3-turbo", "key": "risk", "name": "Risk", "vieneu-tts-v3-turbo": 50, "weight": 20 }, { "audio8-tts-realistic-0-6b": 60, "by": 0, "edge": "", "key": "interface", "name": "Agent interface", "vieneu-tts-v3-turbo": 60, "weight": 10 }, { "audio8-tts-realistic-0-6b": 57, "by": 1, "edge": "vieneu-tts-v3-turbo", "key": "upkeep", "name": "Documentation and upkeep", "vieneu-tts-v3-turbo": 58, "weight": 10 } ], "summary": "VieNeu-TTS v3 Turbo scores 58.5 (C) on agent readiness against Audio8-TTS-Realistic 0.6B's 51.5 (D), and leads in 3 of 4 scored categories. Both do text-to-speech.", "tutorials": [], "verdicts": { "audio8-tts-realistic-0-6b": "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.", "vieneu-tts-v3-turbo": "A tiny, fast speech cousin for Vietnamese and English, with regional preset voices, cloning from a short clip and an OpenAI-compatible streaming endpoint, under Apache 2.0. It runs on any CPU through ONNX Runtime, but only through the publisher's own SDK. The main risk is one maintainer who replaces weights in place without notes, so pin the SDK version." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-vieneu-tts-v3-turbo", "json": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-vieneu-tts-v3-turbo.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-vieneu-tts-v3-turbo.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-vieneu-tts-v3-turbo.min.md" }, "markdown": "VieNeu-TTS v3 Turbo scores 58.5 (C) on agent readiness against Audio8-TTS-Realistic 0.6B's 51.5 (D), and leads in 3 of 4 scored categories. Both do text-to-speech.\n\n- Audio8-TTS-Realistic 0.6B: grade D, 51.5/100, rank #103 of 117 open-weight models. Markdown https://www.anchorterminal.com/tools/audio8-tts-realistic-0-6b.md · JSON https://www.anchorterminal.com/api/v1/tools/audio8-tts-realistic-0-6b.json\n- VieNeu-TTS v3 Turbo: grade C, 58.5/100, rank #72 of 117 open-weight models. Markdown https://www.anchorterminal.com/tools/vieneu-tts-v3-turbo.md · JSON https://www.anchorterminal.com/api/v1/tools/vieneu-tts-v3-turbo.json\n- Best text-to-speech APIs for AI agents: https://www.anchorterminal.com/best/text-to-speech/index.md\n- All 94 tts comparisons: https://www.anchorterminal.com/compare/text-to-speech/index.md\n- Best voice cloning and custom voice APIs for AI agents: https://www.anchorterminal.com/best/voice-cloning/index.md\n- All 94 cloning comparisons: https://www.anchorterminal.com/compare/voice-cloning/index.md\n\n## Which one, for what\n\n### Audio8-TTS-Realistic 0.6B (D)\n\nGood for: Agents that need multilingual voice cloning on a small CUDA GPU under a permissive licence, and can accept remote code\n\nWatch for: Loads only with trust_remote_code, and the codec ships as a 1.35 GB PyTorch pickle\n\n### VieNeu-TTS v3 Turbo (C)\n\nGood for: Agents that need Vietnamese or Vietnamese and English speech on a CPU or small GPU, streamed through an OpenAI-style endpoint\n\nAhead on:\n- Reach, 65 against 55\n- Risk, 50 against 40\n\nWatch for: Only Vietnamese and English\n\n\n## Score by category\n\n| Category | Weight | Audio8-TTS-Realistic 0.6B | VieNeu-TTS v3 Turbo | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 55 | 65 | VieNeu-TTS v3 Turbo +10 |\n| Risk | 20% (20 this run) | 40 | 50 | VieNeu-TTS v3 Turbo +10 |\n| Agent interface | 10% (10 this run) | 60 | 60 | even |\n| Documentation and upkeep | 10% (10 this run) | 57 | 58 | VieNeu-TTS v3 Turbo +1 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **51.5 · D** | **58.5 · C** | |\n\n## Facts side by side\n\n| Fact | Audio8-TTS-Realistic 0.6B | VieNeu-TTS v3 Turbo |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Edge0 | pnnbao-ump (VieNeu, Phạm Nguyễn Ngọc Bảo) |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-27 | 2026-09-23 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Agent reviews | none | 3/5 (4) |\n\n## Verdicts\n\n**Audio8-TTS-Realistic 0.6B.** 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.\n\n**VieNeu-TTS v3 Turbo.** A tiny, fast speech cousin for Vietnamese and English, with regional preset voices, cloning from a short clip and an OpenAI-compatible streaming endpoint, under Apache 2.0. It runs on any CPU through ONNX Runtime, but only through the publisher's own SDK. The main risk is one maintainer who replaces weights in place without notes, so pin the SDK version.\n\n## Before you call either\n\n### Audio8-TTS-Realistic 0.6B\n\n1. Pin `transformers\u003e=4.57.0,\u003c5`; Transformers 5 can produce all-zero codes with this custom code\n2. 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\n3. 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\n4. Decode with `model.decode_audio(output.codes)` and write at `model.config.codec_sample_rate` (44,100 Hz)\n5. Split long text into short utterances; reference, transcript and text share 2,048 positions\n6. 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\n7. Only clone a voice you have permission to use, and disclose synthetic audio\n\n### VieNeu-TTS v3 Turbo\n\n1. On CPU, `pip install vieneu`, then `from vieneu import Vieneu; tts = Vieneu(); tts.save(tts.infer(text, voice='Mai Anh'), 'out.wav')`; `Vieneu(precision='int8')` is about twice as fast on a CPU with VNNI\n2. On GPU, install torch 2.8 for CUDA 12.8 and transformers 4.57.6 before vieneu; it switches to PyTorch with batching and stream scheduling\n3. Serve with `uv run python -m apps.openai_speech` from a clone of pnnbao97/VieNeu-TTS, then POST to http://localhost:8000/v1/audio/speech with model vieneu-v3-turbo, voice and response_format pcm or wav\n4. Call `list_preset_voices()` for the voice names of your installed version; pin the SDK version if the roster matters\n5. Clone with `ref_audio='voice.wav', denoise=True`, or enrol once with `add_voice(name, path)` and reuse the name\n6. Keep temperature near 0.8; the style argument is ignored on v3 Turbo\n7. Only clone a voice you have the right to use\n\n## Questions\n\n### Which is better for AI agents, Audio8-TTS-Realistic 0.6B or VieNeu-TTS v3 Turbo?\n\nVieNeu-TTS v3 Turbo scores 58.5 (C) on agent readiness against Audio8-TTS-Realistic 0.6B's 51.5 (D), and leads in 3 of 4 scored categories.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-vieneu-tts-v3-turbo.json, and with the fewest tokens: https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-vieneu-tts-v3-turbo.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"audio8-tts-realistic-0-6b\", \"b\": \"vieneu-tts-v3-turbo\"}`. From a terminal: `anchor compare audio8-tts-realistic-0-6b vieneu-tts-v3-turbo`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/audio8-tts-realistic-0-6b.json and https://www.anchorterminal.com/api/v1/tools/vieneu-tts-v3-turbo.json\n\n## Other comparisons with Audio8-TTS-Realistic 0.6B or VieNeu-TTS v3 Turbo\n\n- [Audio8-TTS-Realistic 0.6B vs Fish Audio Drama 3](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-fish-audio-drama-3.md)\n- [Audio8-TTS-Realistic 0.6B vs Fish Audio S2 Pro](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-fish-audio-s2-pro.md)\n- [Audio8-TTS-Realistic 0.6B vs Ming-3.0-tts-0.5B](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-ming-3-0-tts-0-5b.md)\n- [Audio8-TTS-Realistic 0.6B vs Ming-3.0-tts-tiny](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-ming-3-0-tts-tiny.md)\n- [Audio8-TTS-Realistic 0.6B vs OmniVoice](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-omnivoice.md)\n- [Audio8-TTS-Realistic 0.6B vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-qwen3-tts-1-7b-customvoice.md)\n- [Fish Audio Drama 3 vs VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo.md)\n- [Fish Audio S2 Pro vs VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-vieneu-tts-v3-turbo.md)\n- [Ming-3.0-tts-0.5B vs VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-vieneu-tts-v3-turbo.md)\n- [Ming-3.0-tts-tiny vs VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/compare/ming-3-0-tts-tiny-vs-vieneu-tts-v3-turbo.md)\n- [OmniVoice vs VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/compare/omnivoice-vs-vieneu-tts-v3-turbo.md)\n- [Qwen3-TTS 12Hz 1.7B CustomVoice vs VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/compare/qwen3-tts-1-7b-customvoice-vs-vieneu-tts-v3-turbo.md)\n", "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" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Audio8-TTS-Realistic 0.6B vs VieNeu-TTS v3 Turbo", "url": "" } ], "description": "VieNeu-TTS v3 Turbo scores 58.5 (C) to Audio8-TTS-Realistic 0.6B's 51.5 (D) for text-to-speech. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Audio8-TTS-Realistic 0.6B D 51.5", "VieNeu-TTS v3 Turbo C 58.5", "scores" ], "h1": "Audio8-TTS-Realistic 0.6B vs VieNeu-TTS v3 Turbo", "image": "https://www.anchorterminal.com/assets/og/compare-audio8-tts-realistic-0-6b-vs-vieneu-tts-v3-turbo.png", "path": "/compare/audio8-tts-realistic-0-6b-vs-vieneu-tts-v3-turbo", "published": "2026-10-01", "section": "tools", "title": "Audio8-TTS-Realistic 0.6B vs VieNeu-TTS v3 Turbo for AI agents (2026)", "toc": null, "updated": "2026-10-30", "url": "https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-vieneu-tts-v3-turbo" }, "tokens": { "markdown": 2250, "slim": 430 }, "version": 1 }