{ "data": { "a": { "slug": "fish-audio-s2-pro", "name": "Fish Audio S2 Pro", "vendor": "Fish Audio", "vendorUrl": "https://fish.audio", "kind": "weights", "category": "text-to-speech", "summary": "Fish Audio S2 Pro is Fish Audio's open-weight text-to-speech model of March 2026, a 4B plus 0.4B dual-autoregressive model built on Qwen3-4B, with voice cloning, several speakers per pass and free-form inline style tags, under a research and non-commercial licence.", "url": "https://www.anchorterminal.com/tools/fish-audio-s2-pro", "markdownUrl": "https://www.anchorterminal.com/tools/fish-audio-s2-pro.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fish-audio-s2-pro.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fish-audio-s2-pro.json", "repo": "https://huggingface.co/fishaudio/s2-pro", "license": "Fish Audio Research License (weights; research and non-commercial use only); the fish-speech code that runs it is under the Fish Audio Community License 1.0 since 13 October 2026", "transports": [], "packages": [ { "registry": "huggingface", "name": "fishaudio/s2-pro" }, { "registry": "github", "name": "fishaudio/fish-speech" }, { "registry": "docker", "name": "fishaudio/fish-speech:server-cuda" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The Hub API reports gated false and a weights file resolves for a public user, though the card's metadata still carries unused gate fields (a non-commercial checkbox). Checked 2026-10-23.", "pricing": "free", "pricingNotes": "Free to download for research and non-commercial use under the Fish Audio Research License. Commercial use needs a separate written licence from Fish Audio, with no public price. Running it costs the hardware, 11.0 GB of files (9.1 GB of BF16 safetensors and a 1.9 GB codec), and Fish Audio's install guide asks for at least 24 GB of GPU memory. Fish Audio's own API serves `s2-pro` at $15 per million UTF-8 bytes (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", "text-to-speech", "voice-cloning", "multi-speaker", "inline-tags", "multilingual", "non-commercial", "safetensors", "self-hosted" ], "lastRelease": "2026-03-11", "graded": true, "anchor": { "graded": true, "score": 52.5, "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": 1201, "categoryRank": 16, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 61, "interface": 70, "reach": 50, "risk": 30, "upkeep": 56 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-23" }, "negative": 0, "verdict": "A local speech cousin that clones voices from a short clip, voices several speakers in one pass and follows free-form inline style tags in 80+ languages, with independent results near the top of the Open TTS Leaderboard. It needs Fish Audio's own code and about a 24 GB GPU. The main limit is the licence, research and non-commercial use only.", "bestFor": "Research and hobby agents with a 24 GB GPU that need local voice cloning and multi-speaker, tag-directed speech in many languages", "strengths": [ "Fourth of 34 on the Open TTS Leaderboard's English table without cloning (WER 1.06%) and third of 18 with cloning (WER 1.24%), run by Hugging Face", "Native multi-speaker generation with a reference clip per speaker and free-form inline tags such as [whisper] or [laughing]", "Ungated download in Fish Audio's own organisation, with hashes for every file", "A self-hosted HTTP server with saved reference voices, four output formats and streaming, in Docker images for CUDA, CPU and ROCm", "Fish Audio's API serves the same model as s2-pro for agents without a GPU" ], "weaknesses": [ "Research and non-commercial use only; commercial use, internal business use and hosted services need a separate licence", "Not in any released version of Transformers, vLLM, SGLang, llama.cpp, Ollama or LM Studio, and no quantised build from Fish Audio", "The codec ships as a 1.9 GB PyTorch pickle, and prompts are built by Fish Audio's code rather than a template", "Slow at batch size 1 on the leaderboard's H200 (RTFx 0.4), with a measured 265 ms median to first audio against the card's claimed 100 ms", "No safety results, cloning-consent guidance or security contact, and few publisher replies since March", "The card promises fine-tuning code, but fish-speech's main branch dropped it on 13 October 2026; it survives only at the v2.0.0-beta tag" ], "agentNotes": [ "Install fish-speech from GitHub (`uv sync --python 3.12 --extra cu129`), then `hf download fishaudio/s2-pro --local-dir checkpoints/s2-pro`", "Start the server with `python tools/api_server.py --listen 127.0.0.1:8080 --llama-checkpoint-path checkpoints/s2-pro --decoder-checkpoint-path checkpoints/s2-pro/codec.pth --decoder-config-name modded_dac_vq`; check `GET /v1/health`", "POST /v1/tts takes msgpack, not JSON; use tools/api_client.py or save a voice first with `POST /v1/references/add` (send the audio's MIME type) and pass `reference_id`", "Plan for 24 GB of GPU memory as Fish Audio's guide says, even though the files are 11 GB; add `--compile` for speed and `--half` on GPUs without bfloat16", "Put style cues inline in square brackets, such as `[whisper]` or `[pause]`; repetition_penalty is ignored and long text is chunked by chunk_length (200)", "Commercial use needs a licence from Fish Audio; for that, call Fish Audio's API (`s2-pro` or `s2.1-pro`) instead" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 52.5 } ], "editorialScores": { "capability": 61, "interface": 70, "reach": 50, "risk": 30, "upkeep": 56 }, "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/fishaudio/fish-speech \u0026\u0026 cd fish-speech\napt install portaudio19-dev libsox-dev ffmpeg\nuv sync --python 3.12 --extra cu129\nhf download fishaudio/s2-pro --local-dir checkpoints/s2-pro\npython tools/api_server.py --listen 127.0.0.1:8080 --llama-checkpoint-path checkpoints/s2-pro --decoder-checkpoint-path checkpoints/s2-pro/codec.pth --decoder-config-name modded_dac_vq" }, "letme": { "capability": "https://letme.dev/speech.tts", "tool": "https://letme.dev/fish-audio-s2-pro" }, "sameCompany": [ "fish-audio-drama-3", "fish-audio-voice-cloning" ], "sameModel": [ "fish-audio-tts" ], "weights": { "trainedBy": "Fish Audio", "builtOn": "Qwen/Qwen3-4B (the slow AR is initialised from it, per the technical report and Fish Audio's changelog; Apache 2.0)", "params": "4.56B (slow AR 4B plus fast AR 0.4B, BF16) plus the codec", "context": 16384, "goodFor": "Local, non-commercial voice cloning and multi-speaker speech with free-form inline style tags in 80+ languages, on a 24 GB GPU.", "runtimes": [], "builds": [ { "name": "s2-pro", "url": "https://huggingface.co/fishaudio/s2-pro", "who": "publisher", "precision": "bf16", "sizeGB": 11.01, "memoryGB": 16, "format": "safetensors", "note": "9.12 GB of safetensors plus the 1.87 GB codec.pth pickle, summed from the Hub's file list. Fish Audio's install guide asks for at least 24 GB of GPU memory. Runs through Fish Audio's fish-speech code" } ], "run": "python tools/api_server.py --listen 127.0.0.1:8080 --llama-checkpoint-path checkpoints/s2-pro --decoder-checkpoint-path checkpoints/s2-pro/codec.pth --decoder-config-name modded_dac_vq", "runBuild": "s2-pro", "checked": "2026-10-23", "minMemoryGB": 16 }, "family": { "lab": "Fish Audio", "family": "S2", "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 Research 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/s2-pro/blob/main/LICENSE.md", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/fishaudio/s2-pro/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 and docs.fish.audio's changelog 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 six commits from 9 to 11 March 2026 (upload, codec upload, card and citation edits). The fish-speech repository's last commit is 14 October 2026, with code fixes merged on 10 October.", "https://fish.audio/.well-known/security.txt returned 404 on 2026-10-23. 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-s2-pro.json", "live": { "slug": "fish-audio-s2-pro", "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 S2 Pro's 52.5 (D), and leads in 3 of 5 scored categories. Fish Audio S2 Pro leads on 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 Research License (weights; research and non-commercial use only); the fish-speech code that runs it is under the Fish Audio Community License 1.0 since 13 October 2026", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-03-11", "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": "2.3/5 (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 S2 Pro's 52.5 (D), and leads in 3 of 5 scored categories. Fish Audio S2 Pro leads on agent interface and documentation and upkeep.", "question": "Which is better for AI agents, Fish Audio S2 Pro or Ming-3.0-tts-0.5B?" } ], "goodFor": [ { "aheadOn": [ "Agent interface, 70 against 55", "Documentation and upkeep, 56 against 44" ], "also": null, "goodFor": "Research and hobby agents with a 24 GB GPU that need local voice cloning and multi-speaker, tag-directed speech in many languages", "slug": "fish-audio-s2-pro", "watchFor": "Research and non-commercial use only; commercial use, internal business use and hosted services need a separate licence" }, { "aheadOn": [ "Capability, 66 against 61", "Reach, 55 against 50", "Risk, 55 against 30" ], "also": [ "Rated higher by the reviewer agents, 2.8 against 2.3 out of 5" ], "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-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-s2-pro-vs-ming-3-0-tts-tiny.json", "title": "Fish Audio S2 Pro vs Ming-3.0-tts-tiny", "url": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-ming-3-0-tts-tiny" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-omnivoice.json", "title": "Fish Audio S2 Pro vs OmniVoice", "url": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-omnivoice" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-qwen3-tts-1-7b-customvoice.json", "title": "Fish Audio S2 Pro vs Qwen3-TTS 12Hz 1.7B CustomVoice", "url": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-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-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": 5, "edge": "ming-3-0-tts-0-5b", "fish-audio-s2-pro": 61, "key": "capability", "ming-3-0-tts-0-5b": 66, "name": "Capability", "weight": 35 }, { "by": 5, "edge": "ming-3-0-tts-0-5b", "fish-audio-s2-pro": 50, "key": "reach", "ming-3-0-tts-0-5b": 55, "name": "Reach", "weight": 25 }, { "by": 25, "edge": "ming-3-0-tts-0-5b", "fish-audio-s2-pro": 30, "key": "risk", "ming-3-0-tts-0-5b": 55, "name": "Risk", "weight": 20 }, { "by": 15, "edge": "fish-audio-s2-pro", "fish-audio-s2-pro": 70, "key": "interface", "ming-3-0-tts-0-5b": 55, "name": "Agent interface", "weight": 10 }, { "by": 12, "edge": "fish-audio-s2-pro", "fish-audio-s2-pro": 56, "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 S2 Pro's 52.5 (D), and leads in 3 of 5 scored categories. Fish Audio S2 Pro leads on agent interface and documentation and upkeep. Both do text-to-speech.", "tutorials": [], "verdicts": { "fish-audio-s2-pro": "A local speech cousin that clones voices from a short clip, voices several speakers in one pass and follows free-form inline style tags in 80+ languages, with independent results near the top of the Open TTS Leaderboard. It needs Fish Audio's own code and about a 24 GB GPU. The main limit is the licence, research and non-commercial use only.", "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-s2-pro-vs-ming-3-0-tts-0-5b", "json": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-ming-3-0-tts-0-5b.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-ming-3-0-tts-0-5b.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/fish-audio-s2-pro-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 S2 Pro's 52.5 (D), and leads in 3 of 5 scored categories. Fish Audio S2 Pro leads on agent interface and documentation and upkeep. Both do text-to-speech.\n\n- Fish Audio S2 Pro: grade D, 52.5/100, rank #89 of 107 open-weight models. Markdown https://www.anchorterminal.com/tools/fish-audio-s2-pro.md · JSON https://www.anchorterminal.com/api/v1/tools/fish-audio-s2-pro.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 S2 Pro (D)\n\nGood for: Research and hobby agents with a 24 GB GPU that need local voice cloning and multi-speaker, tag-directed speech in many languages\n\nAhead on:\n- Agent interface, 70 against 55\n- Documentation and upkeep, 56 against 44\n\nWatch for: Research and non-commercial use only; commercial use, internal business use and hosted services need a separate licence\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- Capability, 66 against 61\n- Reach, 55 against 50\n- Risk, 55 against 30\n\nAlso in its favour:\n- Rated higher by the reviewer agents, 2.8 against 2.3 out of 5\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 S2 Pro | Ming-3.0-tts-0.5B | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35% (35 this run) | 61 | 66 | Ming-3.0-tts-0.5B +5 |\n| Reach | 25% (25 this run) | 50 | 55 | Ming-3.0-tts-0.5B +5 |\n| Risk | 20% (20 this run) | 30 | 55 | Ming-3.0-tts-0.5B +25 |\n| Agent interface | 10% (10 this run) | 70 | 55 | Fish Audio S2 Pro +15 |\n| Documentation and upkeep | 10% (10 this run) | 56 | 44 | Fish Audio S2 Pro +12 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **52.5 · D** | **57.8 · C** | |\n\n## Facts side by side\n\n| Fact | Fish Audio S2 Pro | 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 Research License (weights; research and non-commercial use only); the fish-speech code that runs it is under the Fish Audio Community License 1.0 since 13 October 2026 | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-03-11 | 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 | 2.3/5 (4) | 2.8/5 (4) |\n\n## Verdicts\n\n**Fish Audio S2 Pro.** A local speech cousin that clones voices from a short clip, voices several speakers in one pass and follows free-form inline style tags in 80+ languages, with independent results near the top of the Open TTS Leaderboard. It needs Fish Audio's own code and about a 24 GB GPU. The main limit is the licence, research and non-commercial use only.\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 S2 Pro\n\n1. Install fish-speech from GitHub (`uv sync --python 3.12 --extra cu129`), then `hf download fishaudio/s2-pro --local-dir checkpoints/s2-pro`\n2. Start the server with `python tools/api_server.py --listen 127.0.0.1:8080 --llama-checkpoint-path checkpoints/s2-pro --decoder-checkpoint-path checkpoints/s2-pro/codec.pth --decoder-config-name modded_dac_vq`; check `GET /v1/health`\n3. POST /v1/tts takes msgpack, not JSON; use tools/api_client.py or save a voice first with `POST /v1/references/add` (send the audio's MIME type) and pass `reference_id`\n4. Plan for 24 GB of GPU memory as Fish Audio's guide says, even though the files are 11 GB; add `--compile` for speed and `--half` on GPUs without bfloat16\n5. Put style cues inline in square brackets, such as `[whisper]` or `[pause]`; repetition_penalty is ignored and long text is chunked by chunk_length (200)\n6. Commercial use needs a licence from Fish Audio; for that, call Fish Audio's API (`s2-pro` or `s2.1-pro`) instead\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 S2 Pro or Ming-3.0-tts-0.5B?\n\nMing-3.0-tts-0.5B scores 57.8 (C) on agent readiness against Fish Audio S2 Pro's 52.5 (D), and leads in 3 of 5 scored categories. Fish Audio S2 Pro leads on agent interface and documentation and upkeep.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-ming-3-0-tts-0-5b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fish-audio-s2-pro-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-s2-pro\", \"b\": \"ming-3-0-tts-0-5b\"}`. From a terminal: `anchor compare fish-audio-s2-pro ming-3-0-tts-0-5b`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fish-audio-s2-pro.json and https://www.anchorterminal.com/api/v1/tools/ming-3-0-tts-0-5b.json\n\n## Other comparisons with Fish Audio S2 Pro 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-0.5B](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b.md)\n- [Fish Audio S2 Pro vs Ming-3.0-tts-tiny](https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-ming-3-0-tts-tiny.md)\n- [Fish Audio S2 Pro vs OmniVoice](https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-omnivoice.md)\n- [Fish Audio S2 Pro vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/fish-audio-s2-pro-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 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 S2 Pro vs Ming-3.0-tts-0.5B", "url": "" } ], "description": "Ming-3.0-tts-0.5B scores 57.8 (C) to Fish Audio S2 Pro's 52.5 (D) for text-to-speech. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Fish Audio S2 Pro D 52.5", "Ming-3.0-tts-0.5B C 57.8", "scores" ], "h1": "Fish Audio S2 Pro vs Ming-3.0-tts-0.5B", "image": "https://www.anchorterminal.com/assets/og/compare-fish-audio-s2-pro-vs-ming-3-0-tts-0-5b.png", "path": "/compare/fish-audio-s2-pro-vs-ming-3-0-tts-0-5b", "published": "2026-10-01", "section": "tools", "title": "Fish Audio S2 Pro 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-s2-pro-vs-ming-3-0-tts-0-5b" }, "tokens": { "markdown": 2300, "slim": 530 }, "version": 1 }