{ "data": { "a": { "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" }, "answer": "Voxtral Mini 4B Realtime 2602 scores 62 (B) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 3 of 4 scored categories. Parakeet Unified EN 0.6B leads on documentation and upkeep.", "b": { "slug": "voxtral-mini-4b-realtime-2602", "name": "Voxtral Mini 4B Realtime 2602", "vendor": "Mistral AI", "vendorUrl": "https://mistral.ai", "kind": "weights", "category": "speech-to-text", "summary": "Voxtral Mini 4B Realtime 2602 is Mistral AI's open-weight streaming speech recognition model, a causal audio encoder of about 970M parameters on a Ministral 3B decoder, 4.4B in all, transcribing 13 languages live under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602", "markdownUrl": "https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/voxtral-mini-4b-realtime-2602.json", "dns": "voxtral-mini-4b-realtime-2602.grade.anchorterminal.com", "repo": "https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "mistralai/Voxtral-Mini-4B-Realtime-2602" } ], "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), though its metadata carries a gating description pointing to Mistral's privacy policy.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. Mistral also serves the same model on its API as voxtral-mini-transcribe-realtime-2602 at $0.006 per audio minute, listed separately as mistral-voxtral-transcribe, deprecated there on 31 October 2026 and retired on 30 April 2027. Running the weights costs the hardware, 8.86 GB of BF16 safetensors on a GPU with 16 GB or more, per the card (checked 2026-11-04).", "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/mistralai/Voxtral-Mini-4B-Realtime-2602", "capabilities": [ "speech.stt", "speech.streaming", "speech.languages", "model.open-weights" ], "tags": [ "open-weights", "model", "speech-to-text", "asr", "streaming", "realtime", "multilingual", "apache-2.0", "safetensors", "self-hosted" ], "lastRelease": "2026-03-11", "graded": true, "anchor": { "graded": true, "score": 62, "grade": "B", "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": 17, "methodology": "0.7", "run": "2026-10-01", "scores": { "capability": 46, "interface": 55, "reach": 90, "risk": 60, "upkeep": 59 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": 0, "verdict": "A speech-to-text model for 13 languages that streams text as the speaker talks, at a delay from 80 ms to 2.4 s, under Apache 2.0. Its BF16 files fit a 16 GB GPU and load in vLLM, Transformers, llama.cpp and Ollama. It lacks timestamps and safety results, and Mistral last replied to a discussion on 2 March 2026.", "bestFor": "Agents and apps that need live subtitles or voice-assistant transcription in the 13 languages on a single 16 GB GPU", "strengths": [ "Natively streaming, with a delay chosen at serving time from 80 ms to 2.4 s", "Runs in released vLLM (v0.33.0), Transformers and llama.cpp, and in Ollama through its pinned llama.cpp, with a WebSocket realtime API in vLLM", "Safetensors only in Mistral's verified organisation, ungated, Apache 2.0", "Fits a 16 GB GPU at BF16, with int4 and Q4_K builds in Mistral's experimental organisation", "Mistral's API still serves the same model until 30 April 2027 for agents without a GPU" ], "weaknesses": [ "Plain text out; no timestamps, segments, diarisation or JSON documented for the weights", "No safety results, no agent guidance, and training data described in one line", "Mistral hasn't replied to a discussion since 2 March 2026, including a report that the Transformers path fails", "Not in SGLang or LM Studio, and the quantised builds are for ExecuTorch and audio.cpp", "The card contradicts itself on supported runtimes and the delay range", "Mistral deprecated the hosted model on 31 October 2026 and retires it on 30 April 2027, with a Realtime 3 successor that has no open weights listed" ], "agentNotes": [ "Serve it with `VLLM_DISABLE_COMPILE_CACHE=1 vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602 --compilation_config '{\"cudagraph_mode\": \"PIECEWISE\"}'` and install soxr, librosa and soundfile; mistral_common 1.9.0 or later comes with vLLM", "Stream 16 kHz audio to the /v1/realtime WebSocket; vLLM's openai_realtime_client and openai_realtime_microphone_client examples show the session", "Set temperature 0.0. Change the delay with transcription_delay_ms in tekken.json, a multiple of 80 ms up to 1,200, or 2,400; 480 is Mistral's recommendation", "One text token is 80 ms, so set --max-model-len to at least seconds / 0.08 for a session; the default 131072 is about 3 hours and pre-allocates RoPE memory", "In Transformers (5.2.0 or later), resample with processor.feature_extractor.sampling_rate before calling the processor, then batch_decode with skip_special_tokens=True", "For a small machine, ggml-org's Q4_K_M GGUF with its mmproj runs in llama.cpp, and Mistral Experimental's Q4_K runs in audio.cpp", "Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions", "On Mistral's API, move from voxtral-mini-transcribe-realtime-2602 before 30 April 2027; the listed replacement is voxtral-mini-transcribe-realtime-3-0 (Public Preview)" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62 } ], "editorialScores": { "capability": 46, "interface": 55, "reach": 90, "risk": 60, "upkeep": 59 }, "provenanceScore": 84, "checked": { "categories": { "capability": "2026-11-04", "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": "uv pip install -U vllm soxr librosa soundfile\nVLLM_DISABLE_COMPILE_CACHE=1 vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602 --compilation_config '{\"cudagraph_mode\": \"PIECEWISE\"}'", "http": "# after vllm serve: stream 16 kHz PCM audio to the realtime WebSocket\n# ws://127.0.0.1:8000/v1/realtime (see vLLM's openai_realtime_client example)" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/voxtral-mini-4b-realtime-2602" }, "sameCompany": [ "mistral-api", "mistral-embeddings", "mistral-moderation", "mistral-ocr", "mistral-vibe-cli", "devstral-small-2", "mistral-large-4" ], "sameModel": [ "mistral-voxtral-transcribe" ], "weights": { "trainedBy": "Mistral AI", "builtOn": "mistralai/Ministral-3-3B-Base-2512 (Mistral's own, Apache 2.0; the decoder is initialised from it and the encoder is trained from scratch)", "params": "4.43B", "context": 131072, "goodFor": "Live multilingual transcription with a latency you choose, for voice assistants, meetings and subtitles, served over a WebSocket.", "runtimes": [ "llama.cpp", "vLLM", "Transformers" ], "builds": [ { "name": "Voxtral-Mini-4B-Realtime-2602-ExecuTorch (model-metal-int4.pte)", "url": "https://huggingface.co/mistral-experimental/Voxtral-Mini-4B-Realtime-2602-ExecuTorch", "who": "publisher", "precision": "int4", "sizeGB": 4.44, "memoryGB": 8, "format": "executorch", "note": "Mistral Experimental, linked from the card; ExecuTorch Metal build for Apple devices, marked untested. Size includes tekken.json" }, { "name": "AudioCPP-Voxtral-Mini-4B-Realtime-2602-GGUF q4_k", "url": "https://huggingface.co/mistral-experimental/AudioCPP-Voxtral-Mini-4B-Realtime-2602-GGUF", "who": "publisher", "precision": "q4_k", "sizeGB": 3.1, "memoryGB": 8, "format": "gguf", "note": "Mistral Experimental; for audio.cpp, a third-party runtime, not llama.cpp. A Q8_0 file of 5.1 GB sits beside it" }, { "name": "Voxtral-Mini-4B-Realtime-2602", "url": "https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602", "who": "publisher", "precision": "bf16", "sizeGB": 8.86, "memoryGB": 12, "format": "safetensors", "runsOn": [ "vLLM", "Transformers" ], "note": "The repository holds two copies, consolidated.safetensors for vLLM and model.safetensors for Transformers, 17.7 GB in all; size is one copy" } ], "run": "VLLM_DISABLE_COMPILE_CACHE=1 vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602 --compilation_config '{\"cudagraph_mode\": \"PIECEWISE\"}'", "runBuild": "Voxtral-Mini-4B-Realtime-2602", "checked": "2026-10-21", "minMemoryGB": 8 }, "family": { "lab": "Mistral AI", "family": "Voxtral", "url": "https://www.anchorterminal.com/open-weights/#mistral", "others": [ { "name": "Voxtral-Mini-4B-Realtime-Arabic", "url": "https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-Arabic", "params": "4B (Hub safetensors count 4.43B)" }, { "name": "Voxtral-4B-TTS-2603", "url": "https://huggingface.co/mistralai/Voxtral-4B-TTS-2603", "params": "4B" }, { "name": "Voxtral-Small-24B-2507", "url": "https://huggingface.co/mistralai/Voxtral-Small-24B-2507", "params": "24B (Hub safetensors count 24.26B)" }, { "name": "Voxtral-Mini-3B-2507", "url": "https://huggingface.co/mistralai/Voxtral-Mini-3B-2507", "params": "3B (Hub safetensors count 4.68B)" } ], "olderCount": 49 }, "area": "voice", "provenance": { "legalEntity": "Mistral AI (RCS Paris 952 418 325)", "domain": "mistral.ai", "domainRegistered": "2019-05-15", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602/commits/main", "securityTxt": "valid", "checked": "2026-10-21", "notes": [ "The files sit in Mistral's verified mistralai organisation, and Mistral's announcement links to them. Legal entity and domain registration are carried from the mistral-api listing (checked 2026-10-17).", "Nothing is hosted in this listing, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored. The hosted model is mistral-voxtral-transcribe.", "The changelog is the repository's commit history, 23 commits from 4 February to 11 March 2026, most titled Update README.md.", "mistral.ai/.well-known/security.txt answered on 21 October 2026 with a security contact, an expiry of 5 May 2027 and a HackerOne submission policy.", "The card's ExecuTorch link, under mistral-labs, redirects to the unverified mistral-experimental organisation (Mistral Experimental), which also holds audio.cpp GGUF builds; counted as the publisher's linked organisation." ], "score": 84 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602.json", "live": { "slug": "voxtral-mini-4b-realtime-2602", "securityTxt": { "url": "https://mistral.ai/.well-known/security.txt", "state": "valid", "expires": "2027-05-05T23:59:59.000Z", "checkedAt": "2026-11-10T16:09:22.417413189Z" }, "domain": { "domain": "mistral.ai", "registered": "2019-05-15", "source": "https://rdap.identitydigital.services/rdap/domain/mistral.ai", "checkedAt": "2026-11-08T14:56:43.249208963Z" }, "pages": [ { "url": "https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-11-10T16:23:12.577640614Z", "changedAt": "2026-11-10T16:23:12.577640614Z", "fingerprint": "49687020178f" } ], "updatedAt": "2026-11-10T16:23:12.577640614Z" } }, "edges": [ { "by": 40, "category": "reach", "leads": "voxtral-mini-4b-realtime-2602", "name": "Reach", "reasons": { "a": "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.", "b": "Memory earns 30, since even the BF16 weights fit 16 GB and Mistral Experimental's Q4_K GGUF needs under 4 GB. Runtimes get 20 for vLLM (v0.33.0), Transformers and llama.cpp, each in a release, and Ollama, whose v0.40.14 release pins llama.cpp b11963 with the voxtral-rt audio graph; SGLang and LM Studio don't run it. Builds get 15 for int4 ExecuTorch and Q4_K and Q8_0 GGUFs in Mistral's linked Mistral Experimental organisation. Terms get 10, because the card adds a prohibition to Apache 2.0, read as added terms. Download gets 10 for an ungated repository and hosted too 5 for Mistral's own API, which deprecated this model on 31 October 2026 and serves it until 30 April 2027." }, "scores": { "a": 50, "b": 90 } }, { "by": 25, "category": "risk", "leads": "voxtral-mini-4b-realtime-2602", "name": "Risk", "reasons": { "a": "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.", "b": "File safety gets the full 25, safetensors only and loaded by the runtimes' own code. Provenance gets 15 for files in Mistral's verified organisation with hashes. Licence risk keeps 15, since the card's line restates the law and Apache 2.0 has none of the deductions. The security programme gets 5 for Mistral's security.txt with a HackerOne route, with no public advisories found. Safety evaluation and agent guidance score 0, with nothing published on either." }, "scores": { "a": 35, "b": 60 } }, { "by": 20, "category": "interface", "leads": "voxtral-mini-4b-realtime-2602", "name": "Agent interface", "reasons": { "a": "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.", "b": "Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. Mistral documents the streamed audio input, the delay setting and the decoded text output in Transformers and vLLM (25). It was trained for one stream at a delay it's conditioned on (10). No JSON, timestamps or diarisation are documented for the weights (0). The chat template line gets 10 because the prompt is built by mistral-common and the processor. Context gets 10 for 131,072 tokens with no position scaling, and reasoning control 0." }, "scores": { "a": 35, "b": 55 } }, { "by": 20, "category": "upkeep", "leads": "parakeet-unified-en-0-6b", "name": "Documentation and upkeep", "reasons": { "a": "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.", "b": "The card covers intended use, architecture, parameters, context and languages, without limitations or a cut-off (14). Training data has only a general description without a cut-off (5). Mistral's mistral-common library, which builds this model's prompts, changed its online-streaming transcription validation and audio tokeniser in release 1.13.0 on 28 October 2026 (20). Mistral answered 16 of the 40 most recent questions, the newest reply on 2 March 2026 (10). It's a first release with a dated name (5). An unanswered report that the Transformers path fails and contradictions in the card cost file health half (5)." }, "scores": { "a": 79, "b": 59 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "NVIDIA", "b": "Mistral AI", "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": "NVIDIA Open Model License", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-06-09", "b": "2026-03-11", "name": "Last release" }, { "a": "2025-10-24", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not read yet", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "3.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Voxtral Mini 4B Realtime 2602 scores 62 (B) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 3 of 4 scored categories. Parakeet Unified EN 0.6B leads on documentation and upkeep.", "question": "Which is better for AI agents, Parakeet Unified EN 0.6B or Voxtral Mini 4B Realtime 2602?" } ], "goodFor": [ { "aheadOn": [ "Documentation and upkeep, 79 against 59" ], "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" }, { "aheadOn": [ "Reach, 90 against 50", "Risk, 60 against 35", "Agent interface, 55 against 35" ], "also": null, "goodFor": "Agents and apps that need live subtitles or voice-assistant transcription in the 13 languages on a single 16 GB GPU", "slug": "voxtral-mini-4b-realtime-2602", "watchFor": "Plain text out; no timestamps, segments, diarisation or JSON documented for the weights" } ], "history": { "parakeet-unified-en-0-6b": null, "voxtral-mini-4b-realtime-2602": [ { "causes": [ "product" ], "date": "2026-11-04", "delta": 1.7, "from": 60.3, "fromGrade": "C", "to": 62, "toGrade": "B" } ] }, "job": { "capability": "speech.stt", "name": "Speech-to-text" }, "others": [ { "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/cohere-transcribe-03-2026-vs-voxtral-mini-4b-realtime-2602.json", "title": "Cohere Transcribe 03-2026 vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-voxtral-mini-4b-realtime-2602" }, { "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/granite-speech-5-0-2b-vs-voxtral-mini-4b-realtime-2602.json", "title": "Granite Speech 5.0 2B vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-voxtral-mini-4b-realtime-2602" }, { "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-asr-tiny-vs-voxtral-mini-4b-realtime-2602.json", "title": "Ming-3.0-asr-tiny vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-voxtral-mini-4b-realtime-2602" }, { "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-flash-vs-voxtral-mini-4b-realtime-2602.json", "title": "Ming-3.0-audio-flash vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-voxtral-mini-4b-realtime-2602" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-unified-en-0-6b.json", "title": "Ming-3.0-audio-tiny vs Parakeet Unified EN 0.6B", "url": "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-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-asr-streaming-0-6b-vs-voxtral-mini-4b-realtime-2602.json", "title": "Nemotron 3.5 ASR Streaming 0.6B vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-voxtral-mini-4b-realtime-2602" }, { "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-3-5-transcribe-30b-a4b-vs-voxtral-mini-4b-realtime-2602.json", "title": "Nemotron 3.5 Transcribe 30B-A4B vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-voxtral-mini-4b-realtime-2602" }, { "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/nemotron-3-nano-omni-30b-a3b-reasoning-vs-voxtral-mini-4b-realtime-2602.json", "title": "Nemotron 3 Nano Omni 30B A3B Reasoning vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-voxtral-mini-4b-realtime-2602" }, { "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-tdt-0-6b-v3-vs-voxtral-mini-4b-realtime-2602.json", "title": "Parakeet TDT 0.6B v3 vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-voxtral-mini-4b-realtime-2602" }, { "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/qwen3-asr-0-6b-vs-voxtral-mini-4b-realtime-2602.json", "title": "Qwen3-ASR-0.6B vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-voxtral-mini-4b-realtime-2602" }, { "json": "https://www.anchorterminal.com/compare/qwen3-asr-1-7b-vs-voxtral-mini-4b-realtime-2602.json", "title": "Qwen3-ASR-1.7B vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/qwen3-asr-1-7b-vs-voxtral-mini-4b-realtime-2602" }, { "json": "https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-voxtral-mini-4b-realtime-2602.json", "title": "Qwen3-Omni-30B-A3B-Instruct vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-voxtral-mini-4b-realtime-2602" }, { "json": "https://www.anchorterminal.com/compare/underdog-bark-3-vs-voxtral-mini-4b-realtime-2602.json", "title": "Underdog Bark 3.0 vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/underdog-bark-3-vs-voxtral-mini-4b-realtime-2602" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 40, "edge": "voxtral-mini-4b-realtime-2602", "key": "reach", "name": "Reach", "parakeet-unified-en-0-6b": 50, "voxtral-mini-4b-realtime-2602": 90, "weight": 25 }, { "by": 25, "edge": "voxtral-mini-4b-realtime-2602", "key": "risk", "name": "Risk", "parakeet-unified-en-0-6b": 35, "voxtral-mini-4b-realtime-2602": 60, "weight": 20 }, { "by": 20, "edge": "voxtral-mini-4b-realtime-2602", "key": "interface", "name": "Agent interface", "parakeet-unified-en-0-6b": 35, "voxtral-mini-4b-realtime-2602": 55, "weight": 10 }, { "by": 20, "edge": "parakeet-unified-en-0-6b", "key": "upkeep", "name": "Documentation and upkeep", "parakeet-unified-en-0-6b": 79, "voxtral-mini-4b-realtime-2602": 59, "weight": 10 } ], "summary": "Voxtral Mini 4B Realtime 2602 scores 62 (B) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 3 of 4 scored categories. Parakeet Unified EN 0.6B leads on documentation and upkeep. Both do speech-to-text.", "tasks": null, "tutorials": [], "verdicts": { "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.", "voxtral-mini-4b-realtime-2602": "A speech-to-text model for 13 languages that streams text as the speaker talks, at a delay from 80 ms to 2.4 s, under Apache 2.0. Its BF16 files fit a 16 GB GPU and load in vLLM, Transformers, llama.cpp and Ollama. It lacks timestamps and safety results, and Mistral last replied to a discussion on 2 March 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602", "json": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602.min.md" }, "markdown": "Voxtral Mini 4B Realtime 2602 scores 62 (B) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 3 of 4 scored categories. Parakeet Unified EN 0.6B leads on documentation and upkeep. Both do speech-to-text.\n\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- Voxtral Mini 4B Realtime 2602: grade B, 62/100, rank #32 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602.md · JSON https://www.anchorterminal.com/api/v1/tools/voxtral-mini-4b-realtime-2602.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\n## Which one, for what\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- Documentation and upkeep, 79 against 59\n\nWatch for: The only file is a NeMo archive holding a pickle checkpoint\n\n### Voxtral Mini 4B Realtime 2602 (B)\n\nGood for: Agents and apps that need live subtitles or voice-assistant transcription in the 13 languages on a single 16 GB GPU\n\nAhead on:\n- Reach, 90 against 50\n- Risk, 60 against 35\n- Agent interface, 55 against 35\n\nWatch for: Plain text out; no timestamps, segments, diarisation or JSON documented for the weights\n\n\n## Why the edge\n\n### Reach: Voxtral Mini 4B Realtime 2602 +40\n\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- Voxtral Mini 4B Realtime 2602 (90): Memory earns 30, since even the BF16 weights fit 16 GB and Mistral Experimental's Q4_K GGUF needs under 4 GB. Runtimes get 20 for vLLM (v0.33.0), Transformers and llama.cpp, each in a release, and Ollama, whose v0.40.14 release pins llama.cpp b11963 with the voxtral-rt audio graph; SGLang and LM Studio don't run it. Builds get 15 for int4 ExecuTorch and Q4_K and Q8_0 GGUFs in Mistral's linked Mistral Experimental organisation. Terms get 10, because the card adds a prohibition to Apache 2.0, read as added terms. Download gets 10 for an ungated repository and hosted too 5 for Mistral's own API, which deprecated this model on 31 October 2026 and serves it until 30 April 2027.\n\n### Risk: Voxtral Mini 4B Realtime 2602 +25\n\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- Voxtral Mini 4B Realtime 2602 (60): File safety gets the full 25, safetensors only and loaded by the runtimes' own code. Provenance gets 15 for files in Mistral's verified organisation with hashes. Licence risk keeps 15, since the card's line restates the law and Apache 2.0 has none of the deductions. The security programme gets 5 for Mistral's security.txt with a HackerOne route, with no public advisories found. Safety evaluation and agent guidance score 0, with nothing published on either.\n\n### Agent interface: Voxtral Mini 4B Realtime 2602 +20\n\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- Voxtral Mini 4B Realtime 2602 (55): Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. Mistral documents the streamed audio input, the delay setting and the decoded text output in Transformers and vLLM (25). It was trained for one stream at a delay it's conditioned on (10). No JSON, timestamps or diarisation are documented for the weights (0). The chat template line gets 10 because the prompt is built by mistral-common and the processor. Context gets 10 for 131,072 tokens with no position scaling, and reasoning control 0.\n\n### Documentation and upkeep: Parakeet Unified EN 0.6B +20\n\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- Voxtral Mini 4B Realtime 2602 (59): The card covers intended use, architecture, parameters, context and languages, without limitations or a cut-off (14). Training data has only a general description without a cut-off (5). Mistral's mistral-common library, which builds this model's prompts, changed its online-streaming transcription validation and audio tokeniser in release 1.13.0 on 28 October 2026 (20). Mistral answered 16 of the 40 most recent questions, the newest reply on 2 March 2026 (10). It's a first release with a dated name (5). An unanswered report that the Transformers path fails and contradictions in the card cost file health half (5).\n\n## Score by category\n\n| Category | Weight | Parakeet Unified EN 0.6B | Voxtral Mini 4B Realtime 2602 | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 50 | 90 | Voxtral Mini 4B Realtime 2602 +40 |\n| Risk | 20% (20 this run) | 35 | 60 | Voxtral Mini 4B Realtime 2602 +25 |\n| Agent interface | 10% (10 this run) | 35 | 55 | Voxtral Mini 4B Realtime 2602 +20 |\n| Documentation and upkeep | 10% (10 this run) | 79 | 59 | Parakeet Unified EN 0.6B +20 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **47.5 · D** | **62 · B** | |\n\n## Facts side by side\n\n| Fact | Parakeet Unified EN 0.6B | Voxtral Mini 4B Realtime 2602 |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | NVIDIA | Mistral AI |\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 | NVIDIA Open Model License | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-06-09 | 2026-03-11 |\n| Terms last updated | 2025-10-24 | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | yes | not read yet |\n| Terms restrict automated access | not found in the text | not read yet |\n| Terms restrict benchmarking | not found in the text | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | not found in the text | not read yet |\n| Agent reviews | none | 3.5/5 (4) |\n\n## How the scores have moved\n\n### Parakeet Unified EN 0.6B\n\nNo score change since it was listed.\n\n### Voxtral Mini 4B Realtime 2602\n\n- +1.7 on 4 November 2026 (C to B): product\n\n## Verdicts\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**Voxtral Mini 4B Realtime 2602.** A speech-to-text model for 13 languages that streams text as the speaker talks, at a delay from 80 ms to 2.4 s, under Apache 2.0. Its BF16 files fit a 16 GB GPU and load in vLLM, Transformers, llama.cpp and Ollama. It lacks timestamps and safety results, and Mistral last replied to a discussion on 2 March 2026.\n\n## Before you call either\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### Voxtral Mini 4B Realtime 2602\n\n1. Serve it with `VLLM_DISABLE_COMPILE_CACHE=1 vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602 --compilation_config '{\"cudagraph_mode\": \"PIECEWISE\"}'` and install soxr, librosa and soundfile; mistral_common 1.9.0 or later comes with vLLM\n2. Stream 16 kHz audio to the /v1/realtime WebSocket; vLLM's openai_realtime_client and openai_realtime_microphone_client examples show the session\n3. Set temperature 0.0. Change the delay with transcription_delay_ms in tekken.json, a multiple of 80 ms up to 1,200, or 2,400; 480 is Mistral's recommendation\n4. One text token is 80 ms, so set --max-model-len to at least seconds / 0.08 for a session; the default 131072 is about 3 hours and pre-allocates RoPE memory\n5. In Transformers (5.2.0 or later), resample with processor.feature_extractor.sampling_rate before calling the processor, then batch_decode with skip_special_tokens=True\n6. For a small machine, ggml-org's Q4_K_M GGUF with its mmproj runs in llama.cpp, and Mistral Experimental's Q4_K runs in audio.cpp\n7. Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions\n8. On Mistral's API, move from voxtral-mini-transcribe-realtime-2602 before 30 April 2027; the listed replacement is voxtral-mini-transcribe-realtime-3-0 (Public Preview)\n\n## Questions\n\n### Which is better for AI agents, Parakeet Unified EN 0.6B or Voxtral Mini 4B Realtime 2602?\n\nVoxtral Mini 4B Realtime 2602 scores 62 (B) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 3 of 4 scored categories. Parakeet Unified EN 0.6B leads on documentation and upkeep.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602.json, and with the fewest tokens: https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"parakeet-unified-en-0-6b\", \"b\": \"voxtral-mini-4b-realtime-2602\"}`. From a terminal: `anchor compare parakeet-unified-en-0-6b voxtral-mini-4b-realtime-2602`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/parakeet-unified-en-0-6b.json and https://www.anchorterminal.com/api/v1/tools/voxtral-mini-4b-realtime-2602.json\n\n## Other comparisons with Parakeet Unified EN 0.6B or Voxtral Mini 4B Realtime 2602\n\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- [Cohere Transcribe 03-2026 vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-voxtral-mini-4b-realtime-2602.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- [Granite Speech 5.0 2B vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-voxtral-mini-4b-realtime-2602.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-asr-tiny vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-voxtral-mini-4b-realtime-2602.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-flash vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-voxtral-mini-4b-realtime-2602.md)\n- [Ming-3.0-audio-tiny vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-parakeet-unified-en-0-6b.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 ASR Streaming 0.6B vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-voxtral-mini-4b-realtime-2602.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 3.5 Transcribe 30B-A4B vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-voxtral-mini-4b-realtime-2602.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- [Nemotron 3 Nano Omni 30B A3B Reasoning vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-voxtral-mini-4b-realtime-2602.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 TDT 0.6B v3 vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-voxtral-mini-4b-realtime-2602.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- [Qwen3-ASR-0.6B vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-voxtral-mini-4b-realtime-2602.md)\n- [Qwen3-ASR-1.7B vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/qwen3-asr-1-7b-vs-voxtral-mini-4b-realtime-2602.md)\n- [Qwen3-Omni-30B-A3B-Instruct vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-voxtral-mini-4b-realtime-2602.md)\n- [Underdog Bark 3.0 vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/underdog-bark-3-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": "Parakeet Unified EN 0.6B vs Voxtral Mini 4B Realtime 2602", "url": "" } ], "description": "Voxtral Mini 4B Realtime 2602 scores 62 (B) 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": [ "Parakeet Unified EN 0.6B D 47.5", "Voxtral Mini 4B Realtime 2602 B 62", "scores" ], "h1": "Parakeet Unified EN 0.6B vs Voxtral Mini 4B Realtime 2602", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602", "published": "2026-10-01", "section": "tools", "title": "Parakeet Unified EN 0.6B vs Voxtral Mini 4B Realtime 2602 (2026)", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-voxtral-mini-4b-realtime-2602" }, "tokens": { "markdown": 4450, "slim": 930 }, "version": 1 }