{ "data": { "a": { "slug": "fish-audio-drama-3", "name": "Fish Audio Drama 3", "vendor": "Fish Audio", "vendorUrl": "https://fish.audio", "kind": "weights", "category": "text-to-speech", "summary": "Fish Audio Drama 3 is Fish Audio's open-weight text-to-speech model, a 35B mixture of experts with 3B active built on Qwen3.5-35B-A3B, that clones voices, takes plain-language direction and voices multi-speaker scenes, under the Fish Audio Community License.", "url": "https://www.anchorterminal.com/tools/fish-audio-drama-3", "markdownUrl": "https://www.anchorterminal.com/tools/fish-audio-drama-3.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fish-audio-drama-3.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fish-audio-drama-3.json", "repo": "https://huggingface.co/fishaudio/drama-3", "license": "Fish Audio Community License 1.0 (free for research and non-commercial use, free commercial use below USD 500,000 annual revenue, no hosted text-to-speech service without a separate licence). The card's metadata still names fish-audio-research-license", "transports": [], "packages": [ { "registry": "huggingface", "name": "fishaudio/drama-3" }, { "registry": "huggingface", "name": "fishaudio/drama-3-int4" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. Neither fishaudio/drama-3 nor fishaudio/drama-3-int4 is gated (checked 2026-10-23). The licence says using or accessing the files binds you to it. The fish-speech code is public on GitHub.", "pricing": "free", "pricingNotes": "Free to download. Under the Fish Audio Community License 1.0 (13 October 2026), research and non-commercial use is free, commercial use is free while you and your affiliates have under USD 500,000 annual revenue, and offering it as a hosted text-to-speech, voice or cloning service needs a separate written licence at any size. Running it costs the hardware, an NVIDIA GPU with at least 48 GB for the FP8 build per Fish Audio's install guide. Fish Audio's own API sells `drama-3` at $50 per million UTF-8 bytes, $10 until 12 November 2026 (checked 2026-10-23).", "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 2026-10-23).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-23" }, "docsUrl": "https://speech.fish.audio/inference/", "capabilities": [ "speech.tts", "speech.languages", "speech.streaming", "voice.clone", "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "text-to-speech", "voice-cloning", "multi-speaker", "speech-editing", "inline-tags", "multilingual", "revenue-threshold", "fp8", "int4", "safetensors", "self-hosted", "new" ], "lastRelease": "2026-10-17", "graded": true, "anchor": { "graded": true, "score": 55.6, "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": 1201, "categoryRank": 15, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 67, "interface": 70, "reach": 60, "risk": 25, "upkeep": 51 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-23" }, "negative": 0, "verdict": "A local voice cousin for directed speech, multi-character scenes, voice cloning and word-level edits in about 80 languages. It needs an NVIDIA GPU, about 29 GB for the int4 build or at least 48 GB for FP8, through SGLang-Omni or fish-speech. The main risk is the licence, revocable, capped at USD 500,000 revenue for commercial use and barring hosted services.", "bestFor": "Agents with an NVIDIA GPU of 32 GB or more producing directed multi-character audio, dubbing or narration, for organisations under USD 500,000 revenue or non-commercial use", "strengths": [ "Up to 16 voices per request, cloning from several references, revision by note and word-level editing by infilling, all in one model", "Independently run on the Open TTS Leaderboard, with an English WER of 1.19% without cloning and 2.66% with it", "An int4 build in Fish Audio's organisation that roughly halves the files to 24.0 GB", "Every prompt format and control is written out in the technical report, and SGLang-Omni serves it behind an OpenAI-style speech endpoint with streaming", "Hashed files in Fish Audio's own organisation, ungated" ], "weaknesses": [ "Commercial use is free only below USD 500,000 annual revenue, hosted services always need a separate licence, and the grant is revocable", "The card's licence metadata still names the Research License with a broken link, after a release-day licence switch", "NVIDIA only, and not in any released version of Transformers, vLLM, SGLang, llama.cpp, Ollama or LM Studio", "The codec ships as a PyTorch pickle, and there are no safety results or security contact", "No reply from Fish Audio to any of its 6 Hugging Face discussions" ], "agentNotes": [ "Install SGLang-Omni from source with `uv pip install --prerelease=allow -e \".[fishaudio]\"`, then `sgl-omni serve --model-path fishaudio/drama-3-int4 --port 8000` (or fishaudio/drama-3 for FP8 on 48 GB or more)", "POST JSON to /v1/audio/speech with `input`, optional `references` (audio_path and its transcript) and `previous_takes`; set `response_format` and `stream` for the output", "Start each line with `\u003c|speaker:N|\u003e` (N from 0 to 15) for several voices, and separate lines with `\u003c|audio_separator|\u003e`", "Direct with point tags like `[sighs]`, scoped tags like `\u003cwhisper\u003e...\u003c/whisper\u003e`, a bracketed style prefix, or `Direction:` and `Line:` for a director's note", "The int4 build needs compute capability 8.0 or newer; only the triton attention backend is accepted", "Keep each reference clip under 60 seconds and the prompt under 8,192 rows, about 21.5 rows per second of reference audio", "Check the licence before commercial use or exposing it to other users, and only clone voices with consent", "Treat text from untrusted sources as a script that can carry directions and speaker tags" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 55.6 } ], "editorialScores": { "capability": 67, "interface": 70, "reach": 60, "risk": 25, "upkeep": 51 }, "provenanceScore": 63, "checked": { "categories": { "capability": "2026-10-23", "interface": "2026-10-23", "reach": "2026-10-23", "risk": "2026-10-23", "upkeep": "2026-10-23" }, "last": "2026-10-23", "oldest": "2026-10-23", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "git clone https://github.com/sgl-project/sglang-omni.git \u0026\u0026 cd sglang-omni\nuv venv -p 3.12 .venv \u0026\u0026 . .venv/bin/activate\nuv pip install --prerelease=allow -e \".[fishaudio]\"\nhf download fishaudio/drama-3-int4 # or fishaudio/drama-3 for the FP8 build\nsgl-omni serve --model-path fishaudio/drama-3-int4 --port 8000", "http": "curl -X POST http://localhost:8000/v1/audio/speech \\\n -H \"Content-Type: application/json\" \\\n -d '{\"input\": \"\u003c|speaker:0|\u003e [sighs] Fine. If we miss it, it is on you.\", \"references\": [{\"audio_path\": \"/path/to/reference.wav\", \"text\": \"Transcript of the reference clip.\"}], \"response_format\": \"wav\"}' \\\n --output out.wav" }, "letme": { "capability": "https://letme.dev/speech.tts", "tool": "https://letme.dev/fish-audio-drama-3" }, "sameCompany": [ "fish-audio-s2-pro", "fish-audio-tts", "fish-audio-voice-cloning" ], "weights": { "trainedBy": "Fish Audio", "builtOn": "Qwen/Qwen3.5-35B-A3B (named in the technical report as the backbone it's initialised from, not on the card; Apache 2.0)", "params": "35.9B (35B backbone with about 3B active per token, per the card; 35,899,643,008 by the Hub's count)", "context": 16384, "goodFor": "Directed, expressive speech for multi-character scenes, long-form narration and dubbing, with voice cloning, revision by note and word-level editing, on an NVIDIA GPU.", "runtimes": [], "builds": [ { "name": "drama-3-int4", "url": "https://huggingface.co/fishaudio/drama-3-int4", "who": "publisher", "precision": "int4", "sizeGB": 24, "memoryGB": 32, "format": "safetensors", "note": "W4A16 GPTQ-format experts and attention projections, round-to-nearest with no calibration, quantised by AK (akhaliq) and duplicated into the fishaudio organisation on 14 October 2026; its card calls it unofficial. 22.1 GB of safetensors plus codec.pth, excluding the evaluation audio. Needs compute capability 8.0 or newer" }, { "name": "drama-3", "url": "https://huggingface.co/fishaudio/drama-3", "who": "publisher", "precision": "fp8", "sizeGB": 41.5, "memoryGB": 64, "format": "safetensors", "note": "The release itself, MoE experts in block-scaled FP8 with the rest in BF16, plus the 1.87 GB codec.pth pickle. Fish Audio's install guide asks for at least 48 GB on an NVIDIA GPU" } ], "run": "git clone https://github.com/sgl-project/sglang-omni.git \u0026\u0026 cd sglang-omni \u0026\u0026 uv pip install --prerelease=allow -e \".[fishaudio]\" \u0026\u0026 hf download fishaudio/drama-3-int4 \u0026\u0026 sgl-omni serve --model-path fishaudio/drama-3-int4 --port 8000", "runBuild": "drama-3-int4", "checked": "2026-10-23", "minMemoryGB": 32 }, "family": { "lab": "Fish Audio", "family": "Drama", "url": "https://www.anchorterminal.com/open-weights/#fishaudio", "olderCount": 8 }, "alsoIn": [ "voice-cloning" ], "area": "voice", "provenance": { "legalEntity": "39 AI, Inc. (the licensor named in the Fish Audio Community License). fish.audio's terms of use name Hanabi AI Inc. as the provider of the hosted services", "domain": "fish.audio", "domainRegistered": "2023-12-11", "endpointOnVendorDomain": null, "terms": "https://huggingface.co/fishaudio/drama-3/blob/main/LICENSE", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/fishaudio/drama-3/commits/main", "securityTxt": "none", "checked": "2026-10-23", "notes": [ "The files sit in the fishaudio organisation on Hugging Face, which github.com/fishaudio/fish-speech, the technical report and Fish Audio's launch post link to.", "Nothing is hosted for this listing, so the licence stands in for terms of service and no privacy policy is scored.", "The Hugging Face history is nine commits from 13 to 17 October 2026 (the upload, the licence file and its rename, card edits, the report link and vLLM-Omni instructions). The weights haven't changed since the first commit. fishaudio/drama-3-int4 has two commits on 14 October 2026.", "fish.audio/.well-known/security.txt answered 404 on 23 October 2026 and fishaudio/fish-speech has no SECURITY.md. The domain registration date is carried from the fish-audio-tts check of 17 October 2026." ], "score": 63 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/fish-audio-drama-3.json", "live": { "slug": "fish-audio-drama-3", "securityTxt": { "url": "https://fish.audio/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-23T15:24:36.233836361Z" }, "updatedAt": "2026-10-23T15:24:36.233836361Z" } }, "answer": "VieNeu-TTS v3 Turbo scores 58.5 (C) on agent readiness against Fish Audio Drama 3's 55.6 (C), and leads in 3 of 4 scored categories. Fish Audio Drama 3 leads on agent interface.", "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": 1201, "categoryRank": 10, "methodology": "0.6", "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": "0.6", "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": 53, "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": 53 }, "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": "2026-10-23T07:23:29.716108686Z" } ], "pypiWeekly": 8764, "updatedAt": "2026-10-23T07:23:29.716108686Z" } }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Fish Audio", "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": "Fish Audio Community License 1.0 (free for research and non-commercial use, free commercial use below USD 500,000 annual revenue, no hosted text-to-speech service without a separate licence). The card's metadata still names fish-audio-research-license", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-17", "b": "2026-09-23", "name": "Last release" }, { "a": "", "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": "2.8/5 (4)", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "VieNeu-TTS v3 Turbo scores 58.5 (C) on agent readiness against Fish Audio Drama 3's 55.6 (C), and leads in 3 of 4 scored categories. Fish Audio Drama 3 leads on agent interface.", "question": "Which is better for AI agents, Fish Audio Drama 3 or VieNeu-TTS v3 Turbo?" } ], "goodFor": [ { "aheadOn": [ "Agent interface, 70 against 60" ], "also": null, "goodFor": "Agents with an NVIDIA GPU of 32 GB or more producing directed multi-character audio, dubbing or narration, for organisations under USD 500,000 revenue or non-commercial use", "slug": "fish-audio-drama-3", "watchFor": "Commercial use is free only below USD 500,000 annual revenue, hosted services always need a separate licence, and the grant is revocable" }, { "aheadOn": [ "Reach, 65 against 60", "Risk, 50 against 25", "Documentation and upkeep, 58 against 51" ], "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/fish-audio-drama-3-vs-fish-audio-s2-pro.json", "title": "Fish Audio Drama 3 vs Fish Audio S2 Pro", "url": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-fish-audio-s2-pro" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b.json", "title": "Fish Audio Drama 3 vs Ming-3.0-tts-0.5B", "url": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-tiny.json", "title": "Fish Audio Drama 3 vs Ming-3.0-tts-tiny", "url": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-tiny" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-omnivoice.json", "title": "Fish Audio Drama 3 vs OmniVoice", "url": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-omnivoice" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-qwen3-tts-1-7b-customvoice.json", "title": "Fish Audio Drama 3 vs Qwen3-TTS 12Hz 1.7B CustomVoice", "url": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-qwen3-tts-1-7b-customvoice" }, { "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 }, { "by": 5, "edge": "vieneu-tts-v3-turbo", "fish-audio-drama-3": 60, "key": "reach", "name": "Reach", "vieneu-tts-v3-turbo": 65, "weight": 25 }, { "by": 25, "edge": "vieneu-tts-v3-turbo", "fish-audio-drama-3": 25, "key": "risk", "name": "Risk", "vieneu-tts-v3-turbo": 50, "weight": 20 }, { "by": 10, "edge": "fish-audio-drama-3", "fish-audio-drama-3": 70, "key": "interface", "name": "Agent interface", "vieneu-tts-v3-turbo": 60, "weight": 10 }, { "by": 7, "edge": "vieneu-tts-v3-turbo", "fish-audio-drama-3": 51, "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 Fish Audio Drama 3's 55.6 (C), and leads in 3 of 4 scored categories. Fish Audio Drama 3 leads on agent interface. Both do text-to-speech.", "tutorials": [], "verdicts": { "fish-audio-drama-3": "A local voice cousin for directed speech, multi-character scenes, voice cloning and word-level edits in about 80 languages. It needs an NVIDIA GPU, about 29 GB for the int4 build or at least 48 GB for FP8, through SGLang-Omni or fish-speech. The main risk is the licence, revocable, capped at USD 500,000 revenue for commercial use and barring hosted services.", "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/fish-audio-drama-3-vs-vieneu-tts-v3-turbo", "json": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo.min.md" }, "markdown": "VieNeu-TTS v3 Turbo scores 58.5 (C) on agent readiness against Fish Audio Drama 3's 55.6 (C), and leads in 3 of 4 scored categories. Fish Audio Drama 3 leads on agent interface. Both do text-to-speech.\n\n- Fish Audio Drama 3: grade C, 55.6/100, rank #82 of 107 open-weight models. Markdown https://www.anchorterminal.com/tools/fish-audio-drama-3.md · JSON https://www.anchorterminal.com/api/v1/tools/fish-audio-drama-3.json\n- VieNeu-TTS v3 Turbo: grade C, 58.5/100, rank #69 of 107 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 87 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 87 cloning comparisons: https://www.anchorterminal.com/compare/voice-cloning/index.md\n\n## Which one, for what\n\n### Fish Audio Drama 3 (C)\n\nGood for: Agents with an NVIDIA GPU of 32 GB or more producing directed multi-character audio, dubbing or narration, for organisations under USD 500,000 revenue or non-commercial use\n\nAhead on:\n- Agent interface, 70 against 60\n\nWatch for: Commercial use is free only below USD 500,000 annual revenue, hosted services always need a separate licence, and the grant is revocable\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 60\n- Risk, 50 against 25\n- Documentation and upkeep, 58 against 51\n\nWatch for: Only Vietnamese and English\n\n\n## Score by category\n\n| Category | Weight | Fish Audio Drama 3 | VieNeu-TTS v3 Turbo | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 60 | 65 | VieNeu-TTS v3 Turbo +5 |\n| Risk | 20% (20 this run) | 25 | 50 | VieNeu-TTS v3 Turbo +25 |\n| Agent interface | 10% (10 this run) | 70 | 60 | Fish Audio Drama 3 +10 |\n| Documentation and upkeep | 10% (10 this run) | 51 | 58 | VieNeu-TTS v3 Turbo +7 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **55.6 · C** | **58.5 · C** | |\n\n## Facts side by side\n\n| Fact | Fish Audio Drama 3 | VieNeu-TTS v3 Turbo |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Fish Audio | 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 | Fish Audio Community License 1.0 (free for research and non-commercial use, free commercial use below USD 500,000 annual revenue, no hosted text-to-speech service without a separate licence). The card's metadata still names fish-audio-research-license | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-17 | 2026-09-23 |\n| Terms last updated | | 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 | 2.8/5 (4) | 3/5 (4) |\n\n## Verdicts\n\n**Fish Audio Drama 3.** A local voice cousin for directed speech, multi-character scenes, voice cloning and word-level edits in about 80 languages. It needs an NVIDIA GPU, about 29 GB for the int4 build or at least 48 GB for FP8, through SGLang-Omni or fish-speech. The main risk is the licence, revocable, capped at USD 500,000 revenue for commercial use and barring hosted services.\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### Fish Audio Drama 3\n\n1. Install SGLang-Omni from source with `uv pip install --prerelease=allow -e \".[fishaudio]\"`, then `sgl-omni serve --model-path fishaudio/drama-3-int4 --port 8000` (or fishaudio/drama-3 for FP8 on 48 GB or more)\n2. POST JSON to /v1/audio/speech with `input`, optional `references` (audio_path and its transcript) and `previous_takes`; set `response_format` and `stream` for the output\n3. Start each line with `\u003c|speaker:N|\u003e` (N from 0 to 15) for several voices, and separate lines with `\u003c|audio_separator|\u003e`\n4. Direct with point tags like `[sighs]`, scoped tags like `\u003cwhisper\u003e...\u003c/whisper\u003e`, a bracketed style prefix, or `Direction:` and `Line:` for a director's note\n5. The int4 build needs compute capability 8.0 or newer; only the triton attention backend is accepted\n6. Keep each reference clip under 60 seconds and the prompt under 8,192 rows, about 21.5 rows per second of reference audio\n7. Check the licence before commercial use or exposing it to other users, and only clone voices with consent\n8. Treat text from untrusted sources as a script that can carry directions and speaker tags\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, Fish Audio Drama 3 or VieNeu-TTS v3 Turbo?\n\nVieNeu-TTS v3 Turbo scores 58.5 (C) on agent readiness against Fish Audio Drama 3's 55.6 (C), and leads in 3 of 4 scored categories. Fish Audio Drama 3 leads on agent interface.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"fish-audio-drama-3\", \"b\": \"vieneu-tts-v3-turbo\"}`. From a terminal: `anchor compare fish-audio-drama-3 vieneu-tts-v3-turbo`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fish-audio-drama-3.json and https://www.anchorterminal.com/api/v1/tools/vieneu-tts-v3-turbo.json\n\n## Other comparisons with Fish Audio Drama 3 or VieNeu-TTS v3 Turbo\n\n- [Fish Audio Drama 3 vs Fish Audio S2 Pro](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-fish-audio-s2-pro.md)\n- [Fish Audio Drama 3 vs Ming-3.0-tts-0.5B](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b.md)\n- [Fish Audio Drama 3 vs Ming-3.0-tts-tiny](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-tiny.md)\n- [Fish Audio Drama 3 vs OmniVoice](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-omnivoice.md)\n- [Fish Audio Drama 3 vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-qwen3-tts-1-7b-customvoice.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": "2026-10-23", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.6", "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": "Fish Audio Drama 3 vs VieNeu-TTS v3 Turbo", "url": "" } ], "description": "VieNeu-TTS v3 Turbo scores 58.5 (C) to Fish Audio Drama 3's 55.6 (C) for text-to-speech. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Fish Audio Drama 3 C 55.6", "VieNeu-TTS v3 Turbo C 58.5", "scores" ], "h1": "Fish Audio Drama 3 vs VieNeu-TTS v3 Turbo", "image": "https://www.anchorterminal.com/assets/og/compare-fish-audio-drama-3-vs-vieneu-tts-v3-turbo.png", "path": "/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo", "published": "2026-10-01", "section": "tools", "title": "Fish Audio Drama 3 vs VieNeu-TTS v3 Turbo for AI agents (2026)", "toc": null, "updated": "2026-10-23", "url": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo" }, "tokens": { "markdown": 2350, "slim": 530 }, "version": 1 }