{ "data": { "a": { "slug": "ming-3-0-audio-tiny", "name": "Ming-3.0-audio-tiny", "vendor": "inclusionAI (Ant Group)", "vendorUrl": "https://www.inclusion-ai.org", "kind": "weights", "category": "speech-to-text", "summary": "Ming-3.0-audio-tiny is inclusionAI's open-weight audio-language model for Chinese and English speech recognition, audio understanding and spoken replies, 9.3B parameters with 2.7B active, published on Hugging Face under MIT.", "url": "https://www.anchorterminal.com/tools/ming-3-0-audio-tiny", "markdownUrl": "https://www.anchorterminal.com/tools/ming-3-0-audio-tiny.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/ming-3-0-audio-tiny.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/ming-3-0-audio-tiny.json", "dns": "ming-3-0-audio-tiny.grade.anchorterminal.com", "repo": "https://huggingface.co/inclusionAI/Ming-3.0-audio-tiny", "license": "MIT", "transports": [], "packages": [ { "registry": "huggingface", "name": "inclusionAI/Ming-3.0-audio-tiny" } ], "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). inclusionAI also publishes it on ModelScope.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under MIT. One bundled file, the fastText language-identification model in talker/data, is under CC BY-SA 3.0. inclusionAI sells no per-call access to these weights. Running them costs the hardware, about 20.8 GB of BF16 files (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://huggingface.co/inclusionAI/Ming-3.0-audio-tiny", "capabilities": [ "speech.stt", "speech.batch", "speech.languages", "speech.voices", "voice.speech-to-speech", "voice.tools", "voice.clone", "model.open-weights" ], "tags": [ "open-weights", "speech-to-text", "audio-understanding", "spoken-dialogue", "voice-cloning", "moe", "tool-calling", "chinese", "mit", "safetensors", "self-hosted", "new" ], "lastRelease": "2026-10-20", "graded": true, "anchor": { "graded": true, "score": 52.1, "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": 1518, "categoryRank": 28, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 65, "reach": 45, "risk": 50, "upkeep": 61 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-04" }, "negative": 0, "verdict": "A small MIT-licensed audio-language model that transcribes Chinese and English, answers questions about audio and replies in a built-in or cloned voice. It needs about 25 GB and SGLang-Omni from main or inclusionAI's own vLLM-Omni and SGLang branches. Every loading path runs repository code, and nothing is published on safety.", "bestFor": "Self-hosted Chinese and English transcription, audio questions and spoken replies with tool calls on one GPU with about 25 GB free", "strengths": [ "MIT weights in safetensors, downloadable with no account", "Speech recognition, audio question answering and spoken replies in one 9.3B model with 2.7B active, one GPU for text or ASR", "About 480 built-in voices or a cloned voice from a reference WAV, with streamed speech through vLLM-Omni", "A Jinja chat template with tools, several calls per turn and a per-request thinking switch", "131,072 positions in config.json with no scaling" ], "weaknesses": [ "No named runtime runs it in a released version, only SGLang-Omni main and inclusionAI's own branches", "Every loading path runs repository code, and 40 compiled .pyc files ship under talker/", "BF16 only from inclusionAI, about 25 GB with headroom, and no inference provider", "No tool-call parser named, no JSON or timestamps documented, and no word on where reasoning text comes back", "No safety evaluation, agent guidance, limitations or cut-off on the card, and no security route of its own" ], "agentNotes": [ "Fastest start is SGLang-Omni from main, `sgl-omni serve --model-path inclusionAI/Ming-3.0-audio-tiny --talker.gpu 0`, which exposes OpenAI-style /v1/audio/transcriptions, /v1/audio/speech and /v1/chat/completions", "For transcripts use greedy decoding with 10-gram blocking and the validated ASR prompt, and expect a language label, a tab, then the text", "Parse tool calls yourself from `\u003ctool_call\u003ename` with `\u003carg_key\u003e` and `\u003carg_value\u003e` pairs, since no runtime parser is named", "Thinking is off by default, turn it on with chat_template_kwargs enable_thinking true and strip the `\u003cthink\u003e` block from the reply yourself", "In vLLM-Omni pick a voice with audio.voice id from docs/voices.md, and don't combine it with a reference recording", "Review the repository's Python before passing trust_remote_code, and consider deleting the __pycache__ folders under talker/ so only readable source runs" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 52.1 } ], "editorialScores": { "interface": 65, "reach": 45, "risk": 50, "upkeep": 61 }, "provenanceScore": 39, "checked": { "categories": { "interface": "2026-11-04", "reach": "2026-11-04", "risk": "2026-11-04", "upkeep": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# SGLang-Omni (main branch has the Ming-3.0 audio pipeline); install it per https://sgl-project.github.io/sglang-omni/\nsgl-omni serve --model-path inclusionAI/Ming-3.0-audio-tiny --talker.gpu 0", "http": "curl http://127.0.0.1:8000/v1/audio/transcriptions \\\n -F model=inclusionAI/Ming-3.0-audio-tiny \\\n -F file=@input.wav \\\n -F temperature=0" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/ming-3-0-audio-tiny" }, "sameCompany": [ "ming-3-0-asr-tiny", "ming-3-0-audio-flash", "ming-3-0-tts-tiny", "lbs-27b", "ling-3-0-tiny", "ling-3-1-flash-1019" ], "weights": { "trainedBy": "inclusionAI (Ant Group)", "params": "9.3B", "active": "2.7B", "context": 131072, "goodFor": "Small audio-language model for Chinese and English speech recognition, audio understanding and spoken replies.", "runtimes": [], "builds": [ { "name": "Ming-3.0-audio-tiny", "url": "https://huggingface.co/inclusionAI/Ming-3.0-audio-tiny", "who": "publisher", "precision": "bf16", "sizeGB": 20.7, "memoryGB": 32, "format": "safetensors", "note": "Main shards 17.7 GB plus the Talker and VAE 3.0 GB; runs through SGLang-Omni or inclusionAI's code" } ], "run": "sgl-omni serve --model-path inclusionAI/Ming-3.0-audio-tiny --talker.gpu 0", "runBuild": "Ming-3.0-audio-tiny", "checked": "2026-11-04", "minMemoryGB": 32 }, "family": { "lab": "inclusionAI (Ant Group)", "family": "Ming 3.0", "url": "https://www.anchorterminal.com/open-weights/#inclusionai", "others": [ { "name": "Ming-3.0-tts-0.5B", "url": "https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B", "params": "0.5B (dense)", "listing": "https://www.anchorterminal.com/tools/ming-3-0-tts-0-5b" }, { "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-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-agents" ], "area": "voice", "provenance": { "legalEntity": "", "domain": "inclusion-ai.org", "domainRegistered": "2025-04-03", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/inclusionAI/Ming-3.0-audio-tiny/commits/main", "securityTxt": "none", "checked": "2026-11-04", "notes": [ "The card names inclusionAI as the developer. inclusionAI's GitHub profile describes it as the series of open-source projects from Ant Group. No registered legal entity is named on the card, the repository or the site.", "Nothing is hosted, so the MIT licence stands in for terms of service and no privacy policy is scored.", "The changelog is the repository's commit history, 22 commits from 3 September to 29 October 2026, some of whose messages say what changed (ASR prompt and generation settings on 5 September, voice selection on 19 October, SGLang-Omni serving on 20 October, the training data summary on 21 October). The GitHub repository inclusionAI/Ming-3.0-audio-flash has a fuller history.", "www.inclusion-ai.org/.well-known/security.txt answered 404 on 21 October 2026 and was not re-read on 2026-11-04. The domain registration date is carried from the 21 October 2026 check.", "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": 39 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/ming-3-0-audio-tiny.json", "live": { "slug": "ming-3-0-audio-tiny", "securityTxt": { "url": "https://inclusion-ai.org/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-11-10T16:09:19.556283743Z" }, "domain": { "domain": "inclusion-ai.org", "registered": "2025-04-03", "source": "https://rdap.publicinterestregistry.org/rdap/domain/inclusion-ai.org", "checkedAt": "2026-11-08T15:01:29.637357411Z" }, "pages": [ { "url": "https://huggingface.co/inclusionAI/Ming-3.0-audio-tiny/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-11-10T16:22:56.612856172Z", "changedAt": "2026-11-10T16:22:56.612856172Z", "fingerprint": "a4656682768a" } ], "updatedAt": "2026-11-10T16:22:56.612856172Z" } }, "answer": "Ming-3.0-audio-tiny scores 52.1 (D) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 2 of 4 scored categories. Parakeet Unified EN 0.6B leads on reach and documentation and upkeep.", "b": { "slug": "parakeet-unified-en-0-6b", "name": "Parakeet Unified EN 0.6B", "vendor": "NVIDIA", "vendorUrl": "https://github.com/NVIDIA/NeMo", "kind": "weights", "category": "speech-to-text", "summary": "Parakeet Unified EN 0.6B is NVIDIA's open-weight English speech recognition model, a 600M FastConformer encoder with an RNN-T decoder trained for both offline and streaming use down to 160 ms of latency, with punctuation, published as a NeMo archive.", "url": "https://www.anchorterminal.com/tools/parakeet-unified-en-0-6b", "markdownUrl": "https://www.anchorterminal.com/tools/parakeet-unified-en-0-6b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/parakeet-unified-en-0-6b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/parakeet-unified-en-0-6b.json", "dns": "parakeet-unified-en-0-6b.grade.anchorterminal.com", "repo": "https://huggingface.co/nvidia/parakeet-unified-en-0.6b", "license": "NVIDIA Open Model License", "transports": [], "packages": [ { "registry": "huggingface", "name": "nvidia/parakeet-unified-en-0.6b" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under the NVIDIA Open Model License. Running it yourself costs little hardware, a 2.47 GB NeMo archive in FP32 (checked 2026-11-10).", "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 2026-11-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-10" }, "docsUrl": "https://huggingface.co/nvidia/parakeet-unified-en-0.6b", "capabilities": [ "speech.stt", "speech.batch", "speech.streaming", "model.open-weights" ], "tags": [ "open-weights", "model", "speech-to-text", "asr", "english", "streaming", "fastconformer", "rnnt", "nemo", "nvidia-open-model-license", "self-hosted" ], "lastRelease": "2026-06-09", "graded": true, "anchor": { "graded": true, "score": 47.5, "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": 1518, "categoryRank": 31, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 35, "reach": 50, "risk": 35, "upkeep": 79 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-10" }, "negative": 0, "verdict": "One English model for batch and live transcription, with a well-documented data list and an NVIDIA team that answers. It runs only in NVIDIA NeMo from a pickle-format archive, with no safetensors, GGUF or quantised build, returns plain text without timestamps, and hasn't changed since June.", "bestFor": "English voice agents and captioning that want one small model for both recorded and live audio and already run NeMo", "strengths": [ "One model for offline and streaming transcription, down to 160 ms of latency", "Small: a 2.47 GB file that fits any machine", "Training datasets listed by name with hours", "NVIDIA replied in every discussion on the repository", "A security reporting route and public bulletins from NVIDIA" ], "weaknesses": [ "The only file is a NeMo archive holding a pickle checkpoint", "NVIDIA NeMo is the only runtime; none of the six we count runs it", "No timestamps or other typed output documented", "English only", "A custom licence with a use policy that NVIDIA can change", "No commit since 9 June 2026" ], "agentNotes": [ "Load it with NeMo: `nemo_asr.models.ASRModel.from_pretrained(model_name='nvidia/parakeet-unified-en-0.6b')`, then `transcribe([path])[0].text`", "Loading a .nemo archive unpickles a PyTorch checkpoint, so only load it from NVIDIA's repository", "Send mono wav audio. English only", "For live audio use NeMo's chunked RNN-T streaming script with a 5.6 s left context, and pick the chunk and right context from the card's table", "Below 240 ms of latency accuracy drops, and at 80 ms NVIDIA recommends its nemotron-speech-streaming-en-0.6b instead", "If you need word timestamps, use Parakeet TDT 0.6B v3" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 47.5 } ], "editorialScores": { "interface": 35, "reach": 50, "risk": 35, "upkeep": 79 }, "provenanceScore": 74, "checked": { "categories": { "interface": "2026-11-10", "reach": "2026-11-10", "risk": "2026-11-10", "upkeep": "2026-11-10" }, "last": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install -U \"nemo_toolkit[asr]\"\npython -c \"import nemo.collections.asr as nemo_asr; m = nemo_asr.models.ASRModel.from_pretrained(model_name='nvidia/parakeet-unified-en-0.6b'); print(m.transcribe(['speech.wav'])[0].text)\"", "http": "# no HTTP server ships with it. For streaming, NeMo's script:\npython examples/asr/asr_chunked_inference/rnnt/speech_to_text_streaming_infer_rnnt.py \\\n pretrained_name=nvidia/parakeet-unified-en-0.6b dataset_manifest=manifest.json \\\n left_context_secs=5.6 chunk_secs=0.56 right_context_secs=0.56 att_context_size_as_chunk=true" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/parakeet-unified-en-0-6b" }, "sameCompany": [ "nemotron-3-5-super-vl", "nvidia-nemo-retriever", "nemo-guardrails", "nemotron-3-5-asr-streaming-0-6b", "nemotron-3-5-transcribe-30b-a4b", "parakeet-tdt-0-6b-v3", "nemotron-3-5-parse", "cosmos-reason2-2b", "nemotron-3-5-bolt-e4b-4gb", "nemotron-3-nano-30b-a3b", "nemotron-3-nano-4b", "nemotron-3-nano-omni-30b-a3b-reasoning", "nemotron-3-super-120b-a12b", "nemotron-3-ultra-550b-a55b", "nemotron-3-5-lightning-30b-a3b" ], "weights": { "trainedBy": "NVIDIA", "params": "0.6B", "goodFor": "English transcription from one model in both batch and live use, with punctuation and capitalisation, where latency of 160 ms to 2 s matters.", "runtimes": [], "builds": [ { "name": "parakeet-unified-en-0.6b.nemo", "url": "https://huggingface.co/nvidia/parakeet-unified-en-0.6b/blob/main/parakeet-unified-en-0.6b.nemo", "who": "publisher", "precision": "fp32", "sizeGB": 2.47, "memoryGB": 8, "format": "nemo", "runsOn": [ "NeMo" ], "note": "A NeMo archive holding a PyTorch checkpoint (pickle), loaded by NeMo's ASRModel.from_pretrained. The only build" } ], "run": "python -c \"import nemo.collections.asr as nemo_asr; print(nemo_asr.models.ASRModel.from_pretrained(model_name='nvidia/parakeet-unified-en-0.6b').transcribe(['speech.wav'])[0].text)\"", "runBuild": "parakeet-unified-en-0.6b.nemo", "checked": "2026-11-10", "minMemoryGB": 8 }, "family": { "lab": "NVIDIA (Nemotron)", "family": "Parakeet", "url": "https://www.anchorterminal.com/open-weights/#nvidia", "others": [ { "name": "parakeet-rnnt-1.1b", "url": "https://huggingface.co/nvidia/parakeet-rnnt-1.1b", "params": "1.1B" }, { "name": "parakeet-ctc-1.1b", "url": "https://huggingface.co/nvidia/parakeet-ctc-1.1b", "params": "1.1B" }, { "name": "parakeet-rnnt-0.6b", "url": "https://huggingface.co/nvidia/parakeet-rnnt-0.6b", "params": "0.6B" }, { "name": "parakeet-ctc-0.6b", "url": "https://huggingface.co/nvidia/parakeet-ctc-0.6b", "params": "0.6B" }, { "name": "parakeet-tdt-1.1b", "url": "https://huggingface.co/nvidia/parakeet-tdt-1.1b", "params": "1.1B" }, { "name": "parakeet-tdt_ctc-1.1b", "url": "https://huggingface.co/nvidia/parakeet-tdt_ctc-1.1b", "params": "1.1B" }, { "name": "parakeet-tdt_ctc-0.6b-ja", "url": "https://huggingface.co/nvidia/parakeet-tdt_ctc-0.6b-ja", "params": "0.6B" }, { "name": "parakeet-tdt_ctc-110m", "url": "https://huggingface.co/nvidia/parakeet-tdt_ctc-110m", "params": "110M" }, { "name": "parakeet-tdt-0.6b-v2", "url": "https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2", "params": "0.6B" }, { "name": "parakeet-rnnt-110m-da-dk", "url": "https://huggingface.co/nvidia/parakeet-rnnt-110m-da-dk", "params": "110M" }, { "name": "parakeet-tdt-0.6b-v3", "url": "https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3", "params": "0.6B (627M per the safetensors count)", "listing": "https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3" }, { "name": "parakeet_realtime_eou_120m-v1", "url": "https://huggingface.co/nvidia/parakeet_realtime_eou_120m-v1", "params": "120M" }, { "name": "multitalker-parakeet-streaming-0.6b-v1", "url": "https://huggingface.co/nvidia/multitalker-parakeet-streaming-0.6b-v1", "params": "0.6B" }, { "name": "parakeet-ctc-0.6b-Vietnamese", "url": "https://huggingface.co/nvidia/parakeet-ctc-0.6b-Vietnamese", "params": "0.6B" } ], "olderCount": 47 }, "area": "voice", "provenance": { "legalEntity": "NVIDIA Corporation", "domain": "nvidia.com", "domainRegistered": "1993-04-20", "endpointOnVendorDomain": null, "terms": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/nvidia/parakeet-unified-en-0.6b/commits/main", "securityTxt": "none", "checked": "2026-11-10", "notes": [ "The model sits in NVIDIA's Hugging Face organisation and the card's governing terms are the NVIDIA Open Model License. The domain registration date is carried from the RDAP check made for nemotron-3-nano-30b-a3b on 21 October 2026.", "Nothing is hosted for this listing, so the licence stands in for terms of service and no privacy policy is scored.", "The changelog is the commit history, 19 commits from 7 April to 9 June 2026, mostly card edits.", "www.nvidia.com/.well-known/security.txt answered 403 at the 21 October 2026 check for nemotron-3-nano-30b-a3b. The card links NVIDIA's security vulnerability form." ], "score": 74 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/parakeet-unified-en-0-6b.json" }, "edges": [ { "by": 30, "category": "interface", "leads": "ming-3-0-audio-tiny", "name": "Agent interface", "reasons": { "a": "Read for open weights and, as a speech model, for what it takes and returns, while this model also has a chat interface with function calls. Chat template 20, a Jinja file in the repository. Tool-calling format 10, the format of tool calls comes only from the template and no parser is named, although inclusionAI does document its audio inputs, voices, cloning and output modalities for its own serving branches. Trained tool calling 20, the template renders several calls in one turn and inclusionAI reports function-calling results for Tiny. Structured output 5, transcripts come back in a documented typed form (language label, tab, text) and speech as WAV or streamed PCM, but no JSON, JSON Schema or timestamps are documented. Reasoning control 0, thinking can be turned on per request but nothing says where the reasoning text comes back. Context 10, 131,072 positions in config.json with no scaling, matched by the publisher's vLLM-Omni profiles.", "b": "Chat template 0, no chat template and no prompt. Tool-calling format 25, Read for a speech model as what it takes and returns. Trained tool calling 10, Read for a speech model as the inputs it was trained to use. Structured output 0, Read for a speech model as typed outputs. Reasoning control 0, A speech recognition model with no reasoning. Context 0, no token context is stated. 0 + 25 + 10 + 0 + 0 + 0 = 35." }, "scores": { "a": 65, "b": 35 } }, { "by": 18, "category": "upkeep", "leads": "parakeet-unified-en-0-6b", "name": "Documentation and upkeep", "reasons": { "a": "Model card 11, it covers intended use, architecture, parameters and languages and leaves out limitations, context length and a knowledge cut-off. Training data 15, a summary on the EU AI Act template added on 21 October 2026 names the mix, Ant Spider crawls from March 2024 to May 2026 and the filtering, with sizes only as ranges. Last change 20, the card changed on 29 October 2026. Responsiveness 0, the only discussion is a merged pull request and nobody outside inclusionAI has asked anything yet, and GitHub issues couldn't be checked. Version policy 5, a first release. File health 10, config, template, card and profiles agree and no broken-file report waits. 11 + 15 + 20 + 0 + 5 + 10 = 61.", "b": "Model card 14, Intended use, limitations (buffered streaming only, accuracy falling at 160 ms and below), architecture, parameters (600M) and the language are there. Training data 20, the card lists the training datasets by name, with hours for the four Granary subsets and about 250,000 hours in all, says how the transcripts were made, and NVIDIA publishes Granary on Hugging Face. Last change 10, the last commit to the repository, on 9 June 2026, edited the card, 154 days before this check and within 180. Responsiveness 20, All 5 discussions that aren't pull requests (8 April to 24 June 2026) have a reply from an NVIDIA member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, A first release of the unified model. File health 10, one archive and a card that agree on the model's name, size and NeMo as the way to load it. 14 + 20 + 10 + 20 + 5 + 10 = 79." }, "scores": { "a": 61, "b": 79 } }, { "by": 15, "category": "risk", "leads": "ming-3-0-audio-tiny", "name": "Risk", "reasons": { "a": "File safety 15, safetensors only with no pickle weights, less 10 because every documented way to load it runs the repository's code, and 40 compiled .pyc files sit under talker/. Provenance 15, the files are in inclusionAI's own organisation, which its GitHub repository and card link, and every file has a checksum. Safety evaluation 0, none published. Agent guidance 0, the only caution is about reviewing remote code before loading it. Licence risk 15, MIT with no policy, threshold or revocable terms, and the card's licence link resolves. Security programme 5, for Ant Group's AntSRC reporting centre, read as a company-wide route the way Google's was for Gemma, with no SECURITY.md, security.txt or advisories found.", "b": "File safety 0, the only weights file is parakeet-unified-en-0.6b.nemo, a NeMo archive whose weights are a PyTorch checkpoint read with torch.load, a pickle format, and the card's documented path loads it. Provenance 15, the file sits in NVIDIA's own Hugging Face organisation, the one NVIDIA's NeMo repositories link to (10), and the Hub gives a SHA-256 for the archive and git hashes for the rest (5). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions only. Licence risk 5, 15 less 5 for a use policy beyond the law (NVIDIA's Trustworthy AI terms and the guardrail clause) and 5 for terms the licensor can change or revoke, as read for NVIDIA's other listings under the same licence. Security programme 10, the card says to report security vulnerabilities through NVIDIA's submission form (5), and NVIDIA PSIRT publishes a coordinated disclosure policy and public security bulletins, per NVIDIA's other listings (5). 0 + 15 + 0 + 5 + 5 + 10 = 35." }, "scores": { "a": 50, "b": 35 } }, { "by": 5, "category": "reach", "leads": "parakeet-unified-en-0-6b", "name": "Reach", "reasons": { "a": "Memory 20, the only build inclusionAI publishes is BF16 at 20.78 GB, which with a fifth on top is 24.9 GB, just past the 24 GB band, so it lands in the 32 GB band. Runtimes 0, none of the six named runtimes runs the audio architecture in a released version on 4 November 2026 (vLLM v0.33.0, SGLang v0.5.23, Transformers v5.22.1, llama.cpp b12116 with the text backbone only, Ollama through its llama.cpp pin; LM Studio per 21 October). SGLang-Omni serves it from main but isn't on the list. Builds 0, no quantised build from inclusionAI. Terms 15, plain MIT, with a bundled fastText file under its own CC BY-SA 3.0 notice. Download 10, no gate. Hosted 0, no inference provider on Hugging Face and no inclusionAI API found. 20 + 0 + 0 + 15 + 10 + 0 = 45.", "b": "Memory 30, the only build is the FP32 NeMo archive, 2.47 GB, and 2.47 GB × 1.2 = 3.0 GB, under 16 GB. Runtimes 0, none of the six runs it in a released version. Builds 0, NVIDIA publishes no quantised build of it. Terms 10, the NVIDIA Open Model License is a custom licence, not OSI-approved, that lets anyone use the model commercially for free under a use policy, which is the custom-licence band, as on NVIDIA's other listings. Download 10, the Hub API reports gated false on 10 November 2026, so the file downloads with no account and nothing to accept. Hosted 0, Hugging Face's inference provider mapping is empty on 10 November 2026, and the card names no NVIDIA API that serves it. 30 + 0 + 0 + 10 + 10 + 0 = 50." }, "scores": { "a": 45, "b": 50 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "inclusionAI (Ant Group)", "b": "NVIDIA", "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": "MIT", "b": "NVIDIA Open Model License", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-20", "b": "2026-06-09", "name": "Last release" }, { "a": "no document linked", "b": "2025-10-24", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "yes", "name": "Customer content may train models" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "2.5/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Ming-3.0-audio-tiny scores 52.1 (D) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 2 of 4 scored categories. Parakeet Unified EN 0.6B leads on reach and documentation and upkeep.", "question": "Which is better for AI agents, Ming-3.0-audio-tiny or Parakeet Unified EN 0.6B?" } ], "goodFor": [ { "aheadOn": [ "Risk, 50 against 35", "Agent interface, 65 against 35" ], "also": null, "goodFor": "Self-hosted Chinese and English transcription, audio questions and spoken replies with tool calls on one GPU with about 25 GB free", "slug": "ming-3-0-audio-tiny", "watchFor": "No named runtime runs it in a released version, only SGLang-Omni main and inclusionAI's own branches" }, { "aheadOn": [ "Reach, 50 against 45", "Documentation and upkeep, 79 against 61" ], "also": null, "goodFor": "English voice agents and captioning that want one small model for both recorded and live audio and already run NeMo", "slug": "parakeet-unified-en-0-6b", "watchFor": "The only file is a NeMo archive holding a pickle checkpoint" } ], "history": { "ming-3-0-audio-tiny": [ { "causes": [ "product" ], "date": "2026-11-04", "delta": 2.3, "from": 49.8, "fromGrade": "D", "to": 52.1, "toGrade": "D" } ], "parakeet-unified-en-0-6b": null }, "job": { "capability": "speech.stt", "name": "Speech-to-text" }, "others": [ { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-audio-tiny.json", "title": "Cohere Transcribe 03-2026 vs Ming-3.0-audio-tiny", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-audio-tiny" }, { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-unified-en-0-6b.json", "title": "Cohere Transcribe 03-2026 vs Parakeet Unified EN 0.6B", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-unified-en-0-6b" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-tiny.json", "title": "Granite Speech 5.0 2B vs Ming-3.0-audio-tiny", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-tiny" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-parakeet-unified-en-0-6b.json", "title": "Granite Speech 5.0 2B vs Parakeet Unified EN 0.6B", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-parakeet-unified-en-0-6b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-ming-3-0-audio-tiny.json", "title": "Ming-3.0-asr-tiny vs Ming-3.0-audio-tiny", "url": "https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-ming-3-0-audio-tiny" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-parakeet-unified-en-0-6b.json", "title": "Ming-3.0-asr-tiny vs Parakeet Unified EN 0.6B", "url": "https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-parakeet-unified-en-0-6b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-ming-3-0-audio-tiny.json", "title": "Ming-3.0-audio-flash vs Ming-3.0-audio-tiny", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-ming-3-0-audio-tiny" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-unified-en-0-6b.json", "title": "Ming-3.0-audio-flash vs Parakeet Unified EN 0.6B", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-unified-en-0-6b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-5-asr-streaming-0-6b.json", "title": "Ming-3.0-audio-tiny vs Nemotron 3.5 ASR Streaming 0.6B", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-5-asr-streaming-0-6b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-5-transcribe-30b-a4b.json", "title": "Ming-3.0-audio-tiny vs Nemotron 3.5 Transcribe 30B-A4B", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-5-transcribe-30b-a4b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Ming-3.0-audio-tiny vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-tdt-0-6b-v3.json", "title": "Ming-3.0-audio-tiny vs Parakeet TDT 0.6B v3", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-tdt-0-6b-v3" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-asr-0-6b.json", "title": "Ming-3.0-audio-tiny vs Qwen3-ASR-0.6B", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-asr-0-6b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-asr-1-7b.json", "title": "Ming-3.0-audio-tiny vs Qwen3-ASR-1.7B", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-asr-1-7b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Ming-3.0-audio-tiny vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-underdog-bark-3.json", "title": "Ming-3.0-audio-tiny vs Underdog Bark 3.0", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-underdog-bark-3" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-voxtral-mini-4b-realtime-2602.json", "title": "Ming-3.0-audio-tiny vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-voxtral-mini-4b-realtime-2602" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-parakeet-unified-en-0-6b.json", "title": "Nemotron 3.5 ASR Streaming 0.6B vs Parakeet Unified EN 0.6B", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-parakeet-unified-en-0-6b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-unified-en-0-6b.json", "title": "Nemotron 3.5 Transcribe 30B-A4B vs Parakeet Unified EN 0.6B", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-unified-en-0-6b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-parakeet-unified-en-0-6b.json", "title": "Nemotron 3 Nano Omni 30B A3B Reasoning vs Parakeet Unified EN 0.6B", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-parakeet-unified-en-0-6b" }, { "json": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-parakeet-unified-en-0-6b.json", "title": "Parakeet TDT 0.6B v3 vs Parakeet Unified EN 0.6B", "url": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-parakeet-unified-en-0-6b" }, { "json": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-qwen3-asr-0-6b.json", "title": "Parakeet Unified EN 0.6B vs Qwen3-ASR-0.6B", "url": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-qwen3-asr-0-6b" }, { "json": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-qwen3-asr-1-7b.json", "title": "Parakeet Unified EN 0.6B vs Qwen3-ASR-1.7B", "url": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-qwen3-asr-1-7b" }, { "json": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Parakeet Unified EN 0.6B vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-underdog-bark-3.json", "title": "Parakeet Unified EN 0.6B vs Underdog Bark 3.0", "url": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-underdog-bark-3" }, { "json": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602.json", "title": "Parakeet Unified EN 0.6B vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 5, "edge": "parakeet-unified-en-0-6b", "key": "reach", "ming-3-0-audio-tiny": 45, "name": "Reach", "parakeet-unified-en-0-6b": 50, "weight": 25 }, { "by": 15, "edge": "ming-3-0-audio-tiny", "key": "risk", "ming-3-0-audio-tiny": 50, "name": "Risk", "parakeet-unified-en-0-6b": 35, "weight": 20 }, { "by": 30, "edge": "ming-3-0-audio-tiny", "key": "interface", "ming-3-0-audio-tiny": 65, "name": "Agent interface", "parakeet-unified-en-0-6b": 35, "weight": 10 }, { "by": 18, "edge": "parakeet-unified-en-0-6b", "key": "upkeep", "ming-3-0-audio-tiny": 61, "name": "Documentation and upkeep", "parakeet-unified-en-0-6b": 79, "weight": 10 } ], "summary": "Ming-3.0-audio-tiny scores 52.1 (D) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 2 of 4 scored categories. Parakeet Unified EN 0.6B leads on reach and documentation and upkeep. Both do speech-to-text.", "tasks": null, "tutorials": [], "verdicts": { "ming-3-0-audio-tiny": "A small MIT-licensed audio-language model that transcribes Chinese and English, answers questions about audio and replies in a built-in or cloned voice. It needs about 25 GB and SGLang-Omni from main or inclusionAI's own vLLM-Omni and SGLang branches. Every loading path runs repository code, and nothing is published on safety.", "parakeet-unified-en-0-6b": "One English model for batch and live transcription, with a well-documented data list and an NVIDIA team that answers. It runs only in NVIDIA NeMo from a pickle-format archive, with no safetensors, GGUF or quantised build, returns plain text without timestamps, and hasn't changed since June." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-unified-en-0-6b", "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-unified-en-0-6b.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-unified-en-0-6b.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-unified-en-0-6b.min.md" }, "markdown": "Ming-3.0-audio-tiny scores 52.1 (D) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 2 of 4 scored categories. Parakeet Unified EN 0.6B leads on reach and documentation and upkeep. Both do speech-to-text.\n\n- Ming-3.0-audio-tiny: grade D, 52.1/100, rank #140 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/ming-3-0-audio-tiny.md · JSON https://www.anchorterminal.com/api/v1/tools/ming-3-0-audio-tiny.json\n- Parakeet Unified EN 0.6B: grade D, 47.5/100, rank #154 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/parakeet-unified-en-0-6b.md · JSON https://www.anchorterminal.com/api/v1/tools/parakeet-unified-en-0-6b.json\n- Best speech-to-text APIs for AI agents: https://www.anchorterminal.com/best/speech-to-text/index.md\n- All 386 stt comparisons: https://www.anchorterminal.com/compare/speech-to-text/index.md\n- Best conversational voice-agent APIs: https://www.anchorterminal.com/best/voice-agents/index.md\n- All 581 voice agents comparisons: https://www.anchorterminal.com/compare/voice-agents/index.md\n\n## Which one, for what\n\n### Ming-3.0-audio-tiny (D)\n\nGood for: Self-hosted Chinese and English transcription, audio questions and spoken replies with tool calls on one GPU with about 25 GB free\n\nAhead on:\n- Risk, 50 against 35\n- Agent interface, 65 against 35\n\nWatch for: No named runtime runs it in a released version, only SGLang-Omni main and inclusionAI's own branches\n\n### Parakeet Unified EN 0.6B (D)\n\nGood for: English voice agents and captioning that want one small model for both recorded and live audio and already run NeMo\n\nAhead on:\n- Reach, 50 against 45\n- Documentation and upkeep, 79 against 61\n\nWatch for: The only file is a NeMo archive holding a pickle checkpoint\n\n\n## Why the edge\n\n### Agent interface: Ming-3.0-audio-tiny +30\n\n- Ming-3.0-audio-tiny (65): Read for open weights and, as a speech model, for what it takes and returns, while this model also has a chat interface with function calls. Chat template 20, a Jinja file in the repository. Tool-calling format 10, the format of tool calls comes only from the template and no parser is named, although inclusionAI does document its audio inputs, voices, cloning and output modalities for its own serving branches. Trained tool calling 20, the template renders several calls in one turn and inclusionAI reports function-calling results for Tiny. Structured output 5, transcripts come back in a documented typed form (language label, tab, text) and speech as WAV or streamed PCM, but no JSON, JSON Schema or timestamps are documented. Reasoning control 0, thinking can be turned on per request but nothing says where the reasoning text comes back. Context 10, 131,072 positions in config.json with no scaling, matched by the publisher's vLLM-Omni profiles.\n- Parakeet Unified EN 0.6B (35): Chat template 0, no chat template and no prompt. Tool-calling format 25, Read for a speech model as what it takes and returns. Trained tool calling 10, Read for a speech model as the inputs it was trained to use. Structured output 0, Read for a speech model as typed outputs. Reasoning control 0, A speech recognition model with no reasoning. Context 0, no token context is stated. 0 + 25 + 10 + 0 + 0 + 0 = 35.\n\n### Documentation and upkeep: Parakeet Unified EN 0.6B +18\n\n- Ming-3.0-audio-tiny (61): Model card 11, it covers intended use, architecture, parameters and languages and leaves out limitations, context length and a knowledge cut-off. Training data 15, a summary on the EU AI Act template added on 21 October 2026 names the mix, Ant Spider crawls from March 2024 to May 2026 and the filtering, with sizes only as ranges. Last change 20, the card changed on 29 October 2026. Responsiveness 0, the only discussion is a merged pull request and nobody outside inclusionAI has asked anything yet, and GitHub issues couldn't be checked. Version policy 5, a first release. File health 10, config, template, card and profiles agree and no broken-file report waits. 11 + 15 + 20 + 0 + 5 + 10 = 61.\n- Parakeet Unified EN 0.6B (79): Model card 14, Intended use, limitations (buffered streaming only, accuracy falling at 160 ms and below), architecture, parameters (600M) and the language are there. Training data 20, the card lists the training datasets by name, with hours for the four Granary subsets and about 250,000 hours in all, says how the transcripts were made, and NVIDIA publishes Granary on Hugging Face. Last change 10, the last commit to the repository, on 9 June 2026, edited the card, 154 days before this check and within 180. Responsiveness 20, All 5 discussions that aren't pull requests (8 April to 24 June 2026) have a reply from an NVIDIA member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, A first release of the unified model. File health 10, one archive and a card that agree on the model's name, size and NeMo as the way to load it. 14 + 20 + 10 + 20 + 5 + 10 = 79.\n\n### Risk: Ming-3.0-audio-tiny +15\n\n- Ming-3.0-audio-tiny (50): File safety 15, safetensors only with no pickle weights, less 10 because every documented way to load it runs the repository's code, and 40 compiled .pyc files sit under talker/. Provenance 15, the files are in inclusionAI's own organisation, which its GitHub repository and card link, and every file has a checksum. Safety evaluation 0, none published. Agent guidance 0, the only caution is about reviewing remote code before loading it. Licence risk 15, MIT with no policy, threshold or revocable terms, and the card's licence link resolves. Security programme 5, for Ant Group's AntSRC reporting centre, read as a company-wide route the way Google's was for Gemma, with no SECURITY.md, security.txt or advisories found.\n- Parakeet Unified EN 0.6B (35): File safety 0, the only weights file is parakeet-unified-en-0.6b.nemo, a NeMo archive whose weights are a PyTorch checkpoint read with torch.load, a pickle format, and the card's documented path loads it. Provenance 15, the file sits in NVIDIA's own Hugging Face organisation, the one NVIDIA's NeMo repositories link to (10), and the Hub gives a SHA-256 for the archive and git hashes for the rest (5). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions only. Licence risk 5, 15 less 5 for a use policy beyond the law (NVIDIA's Trustworthy AI terms and the guardrail clause) and 5 for terms the licensor can change or revoke, as read for NVIDIA's other listings under the same licence. Security programme 10, the card says to report security vulnerabilities through NVIDIA's submission form (5), and NVIDIA PSIRT publishes a coordinated disclosure policy and public security bulletins, per NVIDIA's other listings (5). 0 + 15 + 0 + 5 + 5 + 10 = 35.\n\n### Reach: Parakeet Unified EN 0.6B +5\n\n- Ming-3.0-audio-tiny (45): Memory 20, the only build inclusionAI publishes is BF16 at 20.78 GB, which with a fifth on top is 24.9 GB, just past the 24 GB band, so it lands in the 32 GB band. Runtimes 0, none of the six named runtimes runs the audio architecture in a released version on 4 November 2026 (vLLM v0.33.0, SGLang v0.5.23, Transformers v5.22.1, llama.cpp b12116 with the text backbone only, Ollama through its llama.cpp pin; LM Studio per 21 October). SGLang-Omni serves it from main but isn't on the list. Builds 0, no quantised build from inclusionAI. Terms 15, plain MIT, with a bundled fastText file under its own CC BY-SA 3.0 notice. Download 10, no gate. Hosted 0, no inference provider on Hugging Face and no inclusionAI API found. 20 + 0 + 0 + 15 + 10 + 0 = 45.\n- Parakeet Unified EN 0.6B (50): Memory 30, the only build is the FP32 NeMo archive, 2.47 GB, and 2.47 GB × 1.2 = 3.0 GB, under 16 GB. Runtimes 0, none of the six runs it in a released version. Builds 0, NVIDIA publishes no quantised build of it. Terms 10, the NVIDIA Open Model License is a custom licence, not OSI-approved, that lets anyone use the model commercially for free under a use policy, which is the custom-licence band, as on NVIDIA's other listings. Download 10, the Hub API reports gated false on 10 November 2026, so the file downloads with no account and nothing to accept. Hosted 0, Hugging Face's inference provider mapping is empty on 10 November 2026, and the card names no NVIDIA API that serves it. 30 + 0 + 0 + 10 + 10 + 0 = 50.\n\n## Score by category\n\n| Category | Weight | Ming-3.0-audio-tiny | Parakeet Unified EN 0.6B | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 45 | 50 | Parakeet Unified EN 0.6B +5 |\n| Risk | 20% (20 this run) | 50 | 35 | Ming-3.0-audio-tiny +15 |\n| Agent interface | 10% (10 this run) | 65 | 35 | Ming-3.0-audio-tiny +30 |\n| Documentation and upkeep | 10% (10 this run) | 61 | 79 | Parakeet Unified EN 0.6B +18 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **52.1 · D** | **47.5 · D** | |\n\n## Facts side by side\n\n| Fact | Ming-3.0-audio-tiny | Parakeet Unified EN 0.6B |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | inclusionAI (Ant Group) | NVIDIA |\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 | MIT | NVIDIA Open Model License |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-20 | 2026-06-09 |\n| Terms last updated | no document linked | 2025-10-24 |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | not read yet | yes |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Agent reviews | 2.5/5 (4) | none |\n\n## How the scores have moved\n\n### Ming-3.0-audio-tiny\n\n- +2.3 on 4 November 2026: product\n\n### Parakeet Unified EN 0.6B\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Ming-3.0-audio-tiny.** A small MIT-licensed audio-language model that transcribes Chinese and English, answers questions about audio and replies in a built-in or cloned voice. It needs about 25 GB and SGLang-Omni from main or inclusionAI's own vLLM-Omni and SGLang branches. Every loading path runs repository code, and nothing is published on safety.\n\n**Parakeet Unified EN 0.6B.** One English model for batch and live transcription, with a well-documented data list and an NVIDIA team that answers. It runs only in NVIDIA NeMo from a pickle-format archive, with no safetensors, GGUF or quantised build, returns plain text without timestamps, and hasn't changed since June.\n\n## Before you call either\n\n### Ming-3.0-audio-tiny\n\n1. Fastest start is SGLang-Omni from main, `sgl-omni serve --model-path inclusionAI/Ming-3.0-audio-tiny --talker.gpu 0`, which exposes OpenAI-style /v1/audio/transcriptions, /v1/audio/speech and /v1/chat/completions\n2. For transcripts use greedy decoding with 10-gram blocking and the validated ASR prompt, and expect a language label, a tab, then the text\n3. Parse tool calls yourself from `\u003ctool_call\u003ename` with `\u003carg_key\u003e` and `\u003carg_value\u003e` pairs, since no runtime parser is named\n4. Thinking is off by default, turn it on with chat_template_kwargs enable_thinking true and strip the `\u003cthink\u003e` block from the reply yourself\n5. In vLLM-Omni pick a voice with audio.voice id from docs/voices.md, and don't combine it with a reference recording\n6. Review the repository's Python before passing trust_remote_code, and consider deleting the __pycache__ folders under talker/ so only readable source runs\n\n### Parakeet Unified EN 0.6B\n\n1. Load it with NeMo: `nemo_asr.models.ASRModel.from_pretrained(model_name='nvidia/parakeet-unified-en-0.6b')`, then `transcribe([path])[0].text`\n2. Loading a .nemo archive unpickles a PyTorch checkpoint, so only load it from NVIDIA's repository\n3. Send mono wav audio. English only\n4. For live audio use NeMo's chunked RNN-T streaming script with a 5.6 s left context, and pick the chunk and right context from the card's table\n5. Below 240 ms of latency accuracy drops, and at 80 ms NVIDIA recommends its nemotron-speech-streaming-en-0.6b instead\n6. If you need word timestamps, use Parakeet TDT 0.6B v3\n\n## Questions\n\n### Which is better for AI agents, Ming-3.0-audio-tiny or Parakeet Unified EN 0.6B?\n\nMing-3.0-audio-tiny scores 52.1 (D) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 2 of 4 scored categories. Parakeet Unified EN 0.6B leads on reach and documentation and upkeep.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-unified-en-0-6b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-unified-en-0-6b.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"ming-3-0-audio-tiny\", \"b\": \"parakeet-unified-en-0-6b\"}`. From a terminal: `anchor compare ming-3-0-audio-tiny parakeet-unified-en-0-6b`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/ming-3-0-audio-tiny.json and https://www.anchorterminal.com/api/v1/tools/parakeet-unified-en-0-6b.json\n\n## Other comparisons with Ming-3.0-audio-tiny or Parakeet Unified EN 0.6B\n\n- [Cohere Transcribe 03-2026 vs Ming-3.0-audio-tiny](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-audio-tiny.md)\n- [Cohere Transcribe 03-2026 vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-unified-en-0-6b.md)\n- [Granite Speech 5.0 2B vs Ming-3.0-audio-tiny](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-tiny.md)\n- [Granite Speech 5.0 2B vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-parakeet-unified-en-0-6b.md)\n- [Ming-3.0-asr-tiny vs Ming-3.0-audio-tiny](https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-ming-3-0-audio-tiny.md)\n- [Ming-3.0-asr-tiny vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-parakeet-unified-en-0-6b.md)\n- [Ming-3.0-audio-flash vs Ming-3.0-audio-tiny](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-ming-3-0-audio-tiny.md)\n- [Ming-3.0-audio-flash vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-unified-en-0-6b.md)\n- [Ming-3.0-audio-tiny vs Nemotron 3.5 ASR Streaming 0.6B](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-5-asr-streaming-0-6b.md)\n- [Ming-3.0-audio-tiny vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-5-transcribe-30b-a4b.md)\n- [Ming-3.0-audio-tiny vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Ming-3.0-audio-tiny vs Parakeet TDT 0.6B v3](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-tdt-0-6b-v3.md)\n- [Ming-3.0-audio-tiny vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-asr-0-6b.md)\n- [Ming-3.0-audio-tiny vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-asr-1-7b.md)\n- [Ming-3.0-audio-tiny vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Ming-3.0-audio-tiny vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-underdog-bark-3.md)\n- [Ming-3.0-audio-tiny vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-voxtral-mini-4b-realtime-2602.md)\n- [Nemotron 3.5 ASR Streaming 0.6B vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-parakeet-unified-en-0-6b.md)\n- [Nemotron 3.5 Transcribe 30B-A4B vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-unified-en-0-6b.md)\n- [Nemotron 3 Nano Omni 30B A3B Reasoning vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-parakeet-unified-en-0-6b.md)\n- [Parakeet TDT 0.6B v3 vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-parakeet-unified-en-0-6b.md)\n- [Parakeet Unified EN 0.6B vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-qwen3-asr-0-6b.md)\n- [Parakeet Unified EN 0.6B vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-qwen3-asr-1-7b.md)\n- [Parakeet Unified EN 0.6B vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Parakeet Unified EN 0.6B vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-underdog-bark-3.md)\n- [Parakeet Unified EN 0.6B vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602.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": "2026-11-11", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Ming-3.0-audio-tiny vs Parakeet Unified EN 0.6B", "url": "" } ], "description": "Ming-3.0-audio-tiny scores 52.1 (D) to Parakeet Unified EN 0.6B's 47.5 (D) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Ming-3.0-audio-tiny D 52.1", "Parakeet Unified EN 0.6B D 47.5", "scores" ], "h1": "Ming-3.0-audio-tiny vs Parakeet Unified EN 0.6B", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/ming-3-0-audio-tiny-vs-parakeet-unified-en-0-6b", "published": "2026-10-01", "section": "tools", "title": "Ming-3.0-audio-tiny vs Parakeet Unified EN 0.6B for AI agents (2026)", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-unified-en-0-6b" }, "tokens": { "markdown": 4500, "slim": 980 }, "version": 1 }