{ "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": "Ming-3.0-tts-0.5B scores 57.8 (C) on agent readiness against Fish Audio Drama 3's 55.6 (C), and leads in 1 of 5 scored categories. Fish Audio Drama 3 leads on reach, agent interface and documentation and upkeep.", "b": { "slug": "ming-3-0-tts-0-5b", "name": "Ming-3.0-tts-0.5B", "vendor": "inclusionAI (Ant Group)", "vendorUrl": "https://github.com/inclusionAI", "kind": "weights", "category": "text-to-speech", "summary": "Ming-3.0-tts-0.5B is inclusionAI's open-weight text-to-speech model on a Qwen2.5-0.5B backbone, with voice cloning, voice design, built-in voices and inline paralinguistic tags in seven languages, published under MIT and run with inclusionAI's Python code.", "url": "https://www.anchorterminal.com/tools/ming-3-0-tts-0-5b", "markdownUrl": "https://www.anchorterminal.com/tools/ming-3-0-tts-0-5b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/ming-3-0-tts-0-5b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/ming-3-0-tts-0-5b.json", "repo": "https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B", "license": "MIT", "transports": [], "packages": [ { "registry": "huggingface", "name": "inclusionAI/Ming-3.0-tts-0.5B" }, { "registry": "github", "name": "inclusionAI/Ming-3.0-tts" } ], "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 inference code is a public GitHub repository.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under the MIT licence. Running it costs the hardware. The checkpoint is 2.96 GB in BF16, and inclusionAI says it tested inference on NVIDIA H800 80 GB and H20 96 GB with CUDA 12.4 (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/inclusionAI/Ming-3.0-tts", "capabilities": [ "speech.tts", "speech.voices", "speech.languages", "voice.clone", "voice.design", "model.open-weights" ], "tags": [ "open-weights", "text-to-speech", "voice-cloning", "multilingual", "mit", "safetensors", "self-hosted", "python", "new" ], "lastRelease": "2026-10-19", "graded": true, "anchor": { "graded": true, "score": 57.8, "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": 12, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 66, "interface": 55, "reach": 55, "risk": 55, "upkeep": 44 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-21" }, "negative": 0, "verdict": "A small MIT-licensed speech cousin for offline narration, voice cloning and voice design in seven languages and two dialects. It needs about 4 GB but runs only through inclusionAI's own Python scripts on CUDA, with no streaming. The main risk is a loading path that runs the publisher's code, with no safety evaluation or security contact.", "bestFor": "Offline Chinese and English narration, cloning and voice design on a small CUDA GPU, under a plain licence", "strengths": [ "MIT with nothing added, no gate and no account", "2.99 GB in BF16, about 3.6 GB to run, small enough for a laptop GPU", "Eight documented tasks with fixed control values, 100+ Chinese and five English voices, and 14 inline paralinguistic tags", "Safetensors and ONNX only, with a SHA-256 for every large file", "Card and inference code changed two days ago, with a commit history that says what changed" ], "weaknesses": [ "No standard runtime runs it, only inclusionAI's GitHub scripts (mlx-audio and vLLM-Omni aside)", "Loading runs the publisher's code with trust_remote_code, and the prompt is built in code rather than a template", "One task per call, and a whole waveform back with no streaming or timestamps", "No safety evaluation, training data, quantised build or security route of its own", "No hosted route for an agent without a GPU" ], "agentNotes": [ "Clone github.com/inclusionAI/Ming-3.0-tts and `pip install -r requirements.txt` (torch 2.6.0, transformers 4.46.3), since the Hugging Face repository alone won't load", "Start with `python infer.py --model_path inclusionAI/Ming-3.0-tts-0.5B --task IP --text \"The garden will remain open until sunset.\" --ip US_James --use_zero_spk_emb --no_text_normalization --output output/tts.wav`", "Pass `--no_text_normalization` unless pynini 2.1.6 is installed, since text normalisation imports it", "Pick one task per call and pass only that task's controls, since controls from another task are rejected", "Run `python tools/preflight.py --model_path \u003cdir\u003e` to check the checkpoint before the first call", "inclusionAI tested only NVIDIA H800 and H20 with CUDA 12.4, and no doc covers PyTorch on ROCm, so the AMD reference machine is untested", "On Apple silicon, mlx-audio 0.6.1 or later loads mlx-community's conversion, which isn't inclusionAI's", "Clone only voices you have consent for and label the audio as synthetic, as the card asks" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.8 } ], "editorialScores": { "capability": 66, "interface": 55, "reach": 55, "risk": 55, "upkeep": 44 }, "provenanceScore": 53, "checked": { "categories": { "capability": "2026-10-21", "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": "git clone https://github.com/inclusionAI/Ming-3.0-tts.git \u0026\u0026 cd Ming-3.0-tts\npip install -r requirements.txt\npython infer.py --model_path inclusionAI/Ming-3.0-tts-0.5B --task IP \\\n --text \"The garden will remain open until sunset.\" \\\n --ip US_James --use_zero_spk_emb --no_text_normalization --output output/tts.wav" }, "letme": { "capability": "https://letme.dev/speech.tts", "tool": "https://letme.dev/ming-3-0-tts-0-5b" }, "weights": { "trainedBy": "inclusionAI (Ant Group)", "builtOn": "Qwen2.5-0.5B", "params": "0.5B", "goodFor": "Text to speech with voice cloning, voice design, built-in voices and inline paralinguistic tags in seven languages.", "runtimes": [], "builds": [ { "name": "Ming-3.0-tts-0.5B", "url": "https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B", "who": "publisher", "precision": "bf16", "sizeGB": 3, "memoryGB": 8, "format": "safetensors", "note": "Plus a 28 MB ONNX speaker encoder; runs with inclusionAI's PyTorch code, none of the runtimes listed for the machine" } ], "run": "git clone https://github.com/inclusionAI/Ming-3.0-tts.git \u0026\u0026 cd Ming-3.0-tts \u0026\u0026 pip install -r requirements.txt \u0026\u0026 python infer.py --model_path inclusionAI/Ming-3.0-tts-0.5B --task IP --text \"The garden will remain open until sunset.\" --ip US_James --use_zero_spk_emb --no_text_normalization --output output/tts.wav", "runBuild": "Ming-3.0-tts-0.5B", "checked": "2026-10-21", "minMemoryGB": 8 }, "family": { "lab": "inclusionAI (Ant Group)", "family": "Ming 3.0", "url": "https://www.anchorterminal.com/open-weights/#inclusionai", "others": [ { "name": "Ming-3.0-tts-tiny", "url": "https://huggingface.co/inclusionAI/Ming-3.0-tts-tiny", "params": "7.9B total, about 1.3B active (backbone)", "listing": "https://www.anchorterminal.com/tools/ming-3-0-tts-tiny" }, { "name": "Ming-3.0-audio-flash", "url": "https://huggingface.co/inclusionAI/Ming-3.0-audio-flash", "params": "126B total, 6.5B active", "listing": "https://www.anchorterminal.com/tools/ming-3-0-audio-flash" }, { "name": "Ming-3.0-audio-tiny", "url": "https://huggingface.co/inclusionAI/Ming-3.0-audio-tiny", "params": "9.3B total, 2.7B active", "listing": "https://www.anchorterminal.com/tools/ming-3-0-audio-tiny" }, { "name": "Ming-3.0-asr-tiny", "url": "https://huggingface.co/inclusionAI/Ming-3.0-asr-tiny", "params": "not stated on the card (Hub metadata counts 8,865,800,992 in the files)", "listing": "https://www.anchorterminal.com/tools/ming-3-0-asr-tiny" } ], "olderCount": 54 }, "alsoIn": [ "voice-cloning" ], "area": "voice", "provenance": { "legalEntity": "inclusionAI (the LICENSE's copyright holder; source headers read Copyright (c) Ant Group)", "domain": "", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B/commits/main", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "inclusionAI publishes through its Hugging Face organisation (not verified by Hugging Face) and its GitHub organisation, which link to each other. Neither links a website of its own, so no domain is recorded and no security.txt could be looked for.", "Nothing is hosted, so the MIT licence stands in for terms of service and no privacy policy is scored.", "The changelog is the Hugging Face commit history, whose messages say what changed (dialect metrics updated on 15 October, the card's inference instructions aligned with the GitHub release on 19 October). The GitHub repository's history starts with the initial release on 19 October 2026.", "Ant Group runs a company-wide security response centre, AntSRC (https://security.alipay.com/, read on 21 October 2026). Nothing on inclusionAI's card or sites links it." ], "score": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/ming-3-0-tts-0-5b.json", "live": { "slug": "ming-3-0-tts-0-5b", "pages": [ { "url": "https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-10-23T01:49:31.508355292Z", "changedAt": "2026-10-23T01:49:31.508355292Z", "fingerprint": "c3fe372dd04d" } ], "updatedAt": "2026-10-23T01:49:31.508355292Z" } }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Fish Audio", "b": "inclusionAI (Ant Group)", "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": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-17", "b": "2026-10-19", "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": "2.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Ming-3.0-tts-0.5B scores 57.8 (C) on agent readiness against Fish Audio Drama 3's 55.6 (C), and leads in 1 of 5 scored categories. Fish Audio Drama 3 leads on reach, agent interface and documentation and upkeep.", "question": "Which is better for AI agents, Fish Audio Drama 3 or Ming-3.0-tts-0.5B?" } ], "goodFor": [ { "aheadOn": [ "Reach, 60 against 55", "Agent interface, 70 against 55", "Documentation and upkeep, 51 against 44" ], "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": [ "Risk, 55 against 25" ], "also": null, "goodFor": "Offline Chinese and English narration, cloning and voice design on a small CUDA GPU, under a plain licence", "slug": "ming-3-0-tts-0-5b", "watchFor": "No standard runtime runs it, only inclusionAI's GitHub scripts (mlx-audio and vLLM-Omni aside)" } ], "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-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-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-ming-3-0-tts-0-5b.json", "title": "Fish Audio S2 Pro vs Ming-3.0-tts-0.5B", "url": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-ming-3-0-tts-0-5b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-ming-3-0-tts-tiny.json", "title": "Ming-3.0-tts-0.5B vs Ming-3.0-tts-tiny", "url": "https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-ming-3-0-tts-tiny" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-omnivoice.json", "title": "Ming-3.0-tts-0.5B vs OmniVoice", "url": "https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-omnivoice" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-qwen3-tts-1-7b-customvoice.json", "title": "Ming-3.0-tts-0.5B vs Qwen3-TTS 12Hz 1.7B CustomVoice", "url": "https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-qwen3-tts-1-7b-customvoice" }, { "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" } ], "scores": [ { "by": 1, "edge": "fish-audio-drama-3", "fish-audio-drama-3": 67, "key": "capability", "ming-3-0-tts-0-5b": 66, "name": "Capability", "weight": 35 }, { "by": 5, "edge": "fish-audio-drama-3", "fish-audio-drama-3": 60, "key": "reach", "ming-3-0-tts-0-5b": 55, "name": "Reach", "weight": 25 }, { "by": 30, "edge": "ming-3-0-tts-0-5b", "fish-audio-drama-3": 25, "key": "risk", "ming-3-0-tts-0-5b": 55, "name": "Risk", "weight": 20 }, { "by": 15, "edge": "fish-audio-drama-3", "fish-audio-drama-3": 70, "key": "interface", "ming-3-0-tts-0-5b": 55, "name": "Agent interface", "weight": 10 }, { "by": 7, "edge": "fish-audio-drama-3", "fish-audio-drama-3": 51, "key": "upkeep", "ming-3-0-tts-0-5b": 44, "name": "Documentation and upkeep", "weight": 10 } ], "summary": "Ming-3.0-tts-0.5B scores 57.8 (C) on agent readiness against Fish Audio Drama 3's 55.6 (C), and leads in 1 of 5 scored categories. Fish Audio Drama 3 leads on reach, agent interface and documentation and upkeep. 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.", "ming-3-0-tts-0-5b": "A small MIT-licensed speech cousin for offline narration, voice cloning and voice design in seven languages and two dialects. It needs about 4 GB but runs only through inclusionAI's own Python scripts on CUDA, with no streaming. The main risk is a loading path that runs the publisher's code, with no safety evaluation or security contact." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "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-0-5b.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b.min.md" }, "markdown": "Ming-3.0-tts-0.5B scores 57.8 (C) on agent readiness against Fish Audio Drama 3's 55.6 (C), and leads in 1 of 5 scored categories. Fish Audio Drama 3 leads on reach, agent interface and documentation and upkeep. 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- Ming-3.0-tts-0.5B: grade C, 57.8/100, rank #72 of 107 open-weight models. Markdown https://www.anchorterminal.com/tools/ming-3-0-tts-0-5b.md · JSON https://www.anchorterminal.com/api/v1/tools/ming-3-0-tts-0-5b.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- Reach, 60 against 55\n- Agent interface, 70 against 55\n- Documentation and upkeep, 51 against 44\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### Ming-3.0-tts-0.5B (C)\n\nGood for: Offline Chinese and English narration, cloning and voice design on a small CUDA GPU, under a plain licence\n\nAhead on:\n- Risk, 55 against 25\n\nWatch for: No standard runtime runs it, only inclusionAI's GitHub scripts (mlx-audio and vLLM-Omni aside)\n\n\n## Score by category\n\n| Category | Weight | Fish Audio Drama 3 | Ming-3.0-tts-0.5B | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35% (35 this run) | 67 | 66 | Fish Audio Drama 3 +1 |\n| Reach | 25% (25 this run) | 60 | 55 | Fish Audio Drama 3 +5 |\n| Risk | 20% (20 this run) | 25 | 55 | Ming-3.0-tts-0.5B +30 |\n| Agent interface | 10% (10 this run) | 70 | 55 | Fish Audio Drama 3 +15 |\n| Documentation and upkeep | 10% (10 this run) | 51 | 44 | Fish Audio Drama 3 +7 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **55.6 · C** | **57.8 · C** | |\n\n## Facts side by side\n\n| Fact | Fish Audio Drama 3 | Ming-3.0-tts-0.5B |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Fish Audio | inclusionAI (Ant Group) |\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 | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-17 | 2026-10-19 |\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) | 2.8/5 (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**Ming-3.0-tts-0.5B.** A small MIT-licensed speech cousin for offline narration, voice cloning and voice design in seven languages and two dialects. It needs about 4 GB but runs only through inclusionAI's own Python scripts on CUDA, with no streaming. The main risk is a loading path that runs the publisher's code, with no safety evaluation or security contact.\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### Ming-3.0-tts-0.5B\n\n1. Clone github.com/inclusionAI/Ming-3.0-tts and `pip install -r requirements.txt` (torch 2.6.0, transformers 4.46.3), since the Hugging Face repository alone won't load\n2. Start with `python infer.py --model_path inclusionAI/Ming-3.0-tts-0.5B --task IP --text \"The garden will remain open until sunset.\" --ip US_James --use_zero_spk_emb --no_text_normalization --output output/tts.wav`\n3. Pass `--no_text_normalization` unless pynini 2.1.6 is installed, since text normalisation imports it\n4. Pick one task per call and pass only that task's controls, since controls from another task are rejected\n5. Run `python tools/preflight.py --model_path \u003cdir\u003e` to check the checkpoint before the first call\n6. inclusionAI tested only NVIDIA H800 and H20 with CUDA 12.4, and no doc covers PyTorch on ROCm, so the AMD reference machine is untested\n7. On Apple silicon, mlx-audio 0.6.1 or later loads mlx-community's conversion, which isn't inclusionAI's\n8. Clone only voices you have consent for and label the audio as synthetic, as the card asks\n\n## Questions\n\n### Which is better for AI agents, Fish Audio Drama 3 or Ming-3.0-tts-0.5B?\n\nMing-3.0-tts-0.5B scores 57.8 (C) on agent readiness against Fish Audio Drama 3's 55.6 (C), and leads in 1 of 5 scored categories. Fish Audio Drama 3 leads on reach, agent interface and documentation and upkeep.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"fish-audio-drama-3\", \"b\": \"ming-3-0-tts-0-5b\"}`. From a terminal: `anchor compare fish-audio-drama-3 ming-3-0-tts-0-5b`\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/ming-3-0-tts-0-5b.json\n\n## Other comparisons with Fish Audio Drama 3 or Ming-3.0-tts-0.5B\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-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 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 Ming-3.0-tts-0.5B](https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-ming-3-0-tts-0-5b.md)\n- [Ming-3.0-tts-0.5B vs Ming-3.0-tts-tiny](https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-ming-3-0-tts-tiny.md)\n- [Ming-3.0-tts-0.5B vs OmniVoice](https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-omnivoice.md)\n- [Ming-3.0-tts-0.5B vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-qwen3-tts-1-7b-customvoice.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", "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 Ming-3.0-tts-0.5B", "url": "" } ], "description": "Ming-3.0-tts-0.5B scores 57.8 (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", "Ming-3.0-tts-0.5B C 57.8", "scores" ], "h1": "Fish Audio Drama 3 vs Ming-3.0-tts-0.5B", "image": "https://www.anchorterminal.com/assets/og/compare-fish-audio-drama-3-vs-ming-3-0-tts-0-5b.png", "path": "/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b", "published": "2026-10-01", "section": "tools", "title": "Fish Audio Drama 3 vs Ming-3.0-tts-0.5B for AI agents (2026)", "toc": null, "updated": "2026-10-23", "url": "https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b" }, "tokens": { "markdown": 2350, "slim": 530 }, "version": 1 }