{ "data": { "a": { "slug": "cohere-transcribe-03-2026", "name": "Cohere Transcribe 03-2026", "vendor": "Cohere", "vendorUrl": "https://cohere.com", "kind": "weights", "category": "speech-to-text", "summary": "Cohere Transcribe 03-2026 is Cohere's open-weight speech recognition model, a 2B Conformer encoder with a light Transformer decoder trained from scratch, transcribing 14 languages from a pre-specified language, under Apache 2.0, in a gated Hugging Face repository.", "url": "https://www.anchorterminal.com/tools/cohere-transcribe-03-2026", "markdownUrl": "https://www.anchorterminal.com/tools/cohere-transcribe-03-2026.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cohere-transcribe-03-2026.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cohere-transcribe-03-2026.json", "repo": "https://huggingface.co/CohereLabs/cohere-transcribe-03-2026", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "CohereLabs/cohere-transcribe-03-2026" } ], "auth": "none", "authNotes": "The repository is gated (gated: auto on 2026-10-21). The card and file list are public, but the files open only after a signed-in Hugging Face user accepts the conditions, which are approved automatically. We didn't accept them, so this listing is graded from what's public.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0, once the gate is accepted. Cohere also serves the model on its Audio Transcriptions API (free with rate limits on a trial key, or a dedicated Model Vault priced per hour-instance), and fal serves it as a Hugging Face inference provider. Running the weights costs the hardware, 4.13 GB of BF16 safetensors (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://docs.cohere.com/docs/transcribe", "llmsTxt": "https://docs.cohere.com/llms.txt", "capabilities": [ "speech.stt", "speech.batch", "speech.languages", "model.open-weights" ], "tags": [ "open-weights", "model", "speech-to-text", "asr", "conformer", "multilingual", "apache-2.0", "safetensors", "gated", "self-hosted" ], "lastRelease": "2026-04-28", "graded": true, "anchor": { "graded": true, "score": 59.3, "grade": "C", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1197, "categoryRank": 18, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 66, "interface": 45, "reach": 65, "risk": 50, "upkeep": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-21" }, "negative": 0, "verdict": "An accurate offline transcription cousin for 14 languages when the language is known, small enough for about 5 GB, under Apache 2.0, and also on Cohere's API. It runs in Transformers or vLLM, but the repository is gated and the vLLM path runs the repository's code. Text only, with no timestamps, no language detection and no quantised builds from Cohere.", "bestFor": "Agents that need accurate batch transcription of known-language audio in 14 languages on a small GPU", "strengths": [ "Publisher-reported 5.42 average WER on the Open ASR Leaderboard's English sets, with results in the repository to check", "2B parameters, 4.13 GB of BF16 safetensors, about 5 GB in memory", "Native in released Transformers and vLLM, with long-form chunking and batching documented", "Apache 2.0 with nothing added, and Cohere's own API serves the same model", "Every report of a broken file got a reply from Cohere" ], "weaknesses": [ "Gated, so an agent needs a Hugging Face account and must accept the conditions before downloading", "The documented vLLM command uses --trust-remote-code", "No timestamps, diarisation, language detection or JSON output; one language must be given", "No quantised build from Cohere and no llama.cpp, Ollama or LM Studio support", "No safety results, training data without sources or cut-off, and no replies in the repository since April" ], "agentNotes": [ "A person has to accept the conditions on the Hugging Face page with an account, then `hf auth login`, before the files download", "Offline, `pip install \"transformers\u003e=5.4.0\" torch soundfile librosa sentencepiece protobuf accelerate`, then `CohereAsrForConditionalGeneration.from_pretrained(\"CohereLabs/cohere-transcribe-03-2026\", device_map=\"auto\")` with no remote code", "Always pass language= (en, de, fr, it, es, pt, el, nl, pl, zh, ja, ko, vi, ar); there's no auto-detection", "For long audio, keep audio_chunk_index from the processor and pass it to processor.decode to reassemble the chunks", "Serving, `vllm serve CohereLabs/cohere-transcribe-03-2026 --trust-remote-code`, then POST to /v1/audio/transcriptions", "Put voice activity detection in front of it, since it transcribes noise and can hallucinate on silence", "Without the hardware or the gate, Cohere's API serves the same model as cohere-transcribe-03-2026", "Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.3 } ], "editorialScores": { "capability": 66, "interface": 45, "reach": 65, "risk": 50, "upkeep": 54 }, "provenanceScore": 73, "checked": { "categories": { "capability": "2026-10-21", "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# accept the conditions on the Hugging Face page first, then log in with hf auth login\npip install \"transformers\u003e=5.4.0\" torch soundfile librosa sentencepiece protobuf accelerate", "http": "# after: vllm serve CohereLabs/cohere-transcribe-03-2026 --trust-remote-code\ncurl -X POST http://localhost:8000/v1/audio/transcriptions \\\n -F file=@/path/to/speech.wav \\\n -F model=CohereLabs/cohere-transcribe-03-2026" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/cohere-transcribe-03-2026" }, "sameCompany": [ "cohere-chat", "cohere-embed", "cohere-north" ], "weights": { "trainedBy": "Cohere (Cohere Labs)", "params": "2.07B", "goodFor": "Accurate offline and batch transcription in 14 languages when the language is known, on a small GPU.", "runtimes": [ "vLLM", "Transformers" ], "builds": [ { "name": "cohere-transcribe-03-2026", "url": "https://huggingface.co/CohereLabs/cohere-transcribe-03-2026", "who": "publisher", "precision": "bf16", "sizeGB": 4.13, "memoryGB": 8, "format": "safetensors", "runsOn": [ "vLLM", "Transformers" ], "note": "Gated, a click-through with automatic approval that needs a Hugging Face account" } ], "run": "vllm serve CohereLabs/cohere-transcribe-03-2026 --trust-remote-code", "runBuild": "cohere-transcribe-03-2026", "checked": "2026-10-21", "minMemoryGB": 8 }, "family": { "lab": "Cohere (Cohere Labs)", "family": "Cohere Transcribe", "url": "https://www.anchorterminal.com/open-weights/#cohere", "others": [ { "name": "cohere-transcribe-arabic-07-2026", "url": "https://huggingface.co/CohereLabs/cohere-transcribe-arabic-07-2026", "params": "2.07B (Hub safetensors count; the name states none)" } ], "olderCount": 29 }, "area": "voice", "provenance": { "legalEntity": "Cohere Inc.", "domain": "cohere.com", "domainRegistered": "2000-03-07", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://docs.cohere.com/changelog/cohere-transcribe-03-2026", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "The card says Developed by Cohere and Cohere Labs. The files sit in the verified CohereLabs organisation, which cohere.com's Transcribe announcement links to. Legal entity and domain registration are carried from the cohere-chat listing (checked 2026-10-09).", "Nothing is hosted in this listing, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored. Cohere's own API serves the model; no Cohere transcription API is listed here yet.", "The repository's commit history is behind the gate. Per-file last commits from the public file list show the weights from 25 March 2026, tokenizer fixes on 27 March, a modeling fix on 26 March, a configuration change on 28 April and card edits up to 7 October 2026.", "cohere.com/.well-known/security.txt answered 404 on 21 October 2026. The cohere-chat listing records a responsible disclosure policy and bug bounty in Cohere's trust centre." ], "score": 73 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cohere-transcribe-03-2026.json" }, "answer": "Parakeet TDT 0.6B v3 scores 66.9 (B) on agent readiness against Cohere Transcribe 03-2026's 59.3 (C), and leads in 4 of 5 scored categories.", "b": { "slug": "parakeet-tdt-0-6b-v3", "name": "Parakeet TDT 0.6B v3", "vendor": "NVIDIA", "vendorUrl": "https://github.com/NVIDIA/NeMo", "kind": "weights", "category": "speech-to-text", "summary": "Parakeet TDT 0.6B v3 is NVIDIA's open-weight speech recognition model for 25 European languages, a 0.6B-parameter FastConformer encoder with a TDT decoder that detects the language and returns punctuated text with word and segment timestamps, under CC BY 4.0.", "url": "https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3", "markdownUrl": "https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/parakeet-tdt-0-6b-v3.json", "repo": "https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3", "license": "CC-BY-4.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "nvidia/parakeet-tdt-0.6b-v3" } ], "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).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under CC BY 4.0, which asks for attribution. Running it costs the hardware; the card says at least 2 GB of RAM to load it. The files are 2.5 GB in FP32 safetensors or 0.7 GB as NVIDIA's Q8_0 GGUF (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/nvidia/parakeet-tdt-0.6b-v3", "capabilities": [ "speech.stt", "speech.batch", "speech.streaming", "speech.languages", "model.open-weights" ], "tags": [ "open-weights", "model", "speech-to-text", "asr", "multilingual", "timestamps", "fastconformer", "tdt", "nemo", "cc-by-4.0", "safetensors", "gguf", "self-hosted" ], "lastRelease": "2026-08-05", "graded": true, "anchor": { "graded": true, "score": 66.9, "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": 1197, "categoryRank": 11, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 74, "interface": 50, "reach": 65, "risk": 60, "upkeep": 77 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-21" }, "negative": 0, "verdict": "A small, fast transcription cousin for 25 European languages that detects the language and returns punctuated text with word timestamps. It fits in under 1 GB as NVIDIA's GGUF and runs in Transformers, NeMo or NVIDIA's C++ runtime, under CC BY 4.0. Few other runtimes load it, and it takes no language hint.", "bestFor": "Agents that need cheap local transcription with timestamps in English and other European languages", "strengths": [ "Small enough for any machine, 0.71 GB as NVIDIA's Q8_0 GGUF or 2.5 GB in FP32", "25 European languages detected automatically, with punctuation, capitalisation and word, segment and char timestamps", "CC BY 4.0, ungated, files hashed in NVIDIA's own organisation", "Training data listed by corpus with hours, much of it published as Granary", "Kept current, with Transformers support added in 2026 and NVIDIA's C++ runtime changing this month" ], "weaknesses": [ "Among the six runtimes only Transformers runs it; vLLM, SGLang, llama.cpp, Ollama and LM Studio don't", "The NeMo archive, the card's main path, loads a PyTorch pickle", "No language hint or hotwords, and an open report's title says it can drift into other languages without one", "No safety results and only general cautions", "NVIDIA answered 9 of the 40 latest questions, none since February 2026" ], "agentNotes": [ "For the smallest setup, `hf download nvidia/parakeet-tdt-0.6b-v3 parakeet-tdt-0.6b-v3.q8_0.gguf --local-dir models`, then `nemo-speech transcribe speech.wav --model models/parakeet-tdt-0.6b-v3.q8_0.gguf` with NeMo-Speech.cpp", "In Python, `pipeline('automatic-speech-recognition', model='nvidia/parakeet-tdt-0.6b-v3')` works on Transformers 5.10.0 or later, despite the card's note to install from source", "Resample to 16 kHz mono first; it takes wav or flac", "Ask for timestamps with `timestamps=True` in NeMo, or pass `durations=output.durations` to `processor.decode` in Transformers", "For audio longer than about 24 minutes, switch NeMo to local attention with `change_attention_model(\"rel_pos_local_attn\", [256, 256])`", "Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 4, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 66.9 } ], "editorialScores": { "capability": 74, "interface": 50, "reach": 65, "risk": 60, "upkeep": 77 }, "provenanceScore": 73, "checked": { "categories": { "capability": "2026-10-21", "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install -U \"transformers\u003e=5.10\" torch\npython -c \"from transformers import pipeline; print(pipeline('automatic-speech-recognition', model='nvidia/parakeet-tdt-0.6b-v3')('speech.wav'))\"\n# or with NVIDIA's C++ runtime, NeMo-Speech.cpp:\nhf download nvidia/parakeet-tdt-0.6b-v3 parakeet-tdt-0.6b-v3.q8_0.gguf --local-dir models\nnemo-speech transcribe speech.wav --model models/parakeet-tdt-0.6b-v3.q8_0.gguf", "http": "# after starting NeMo-Speech.cpp's server with this model (it binds 127.0.0.1:8080)\ncurl http://127.0.0.1:8080/v1/audio/transcriptions -F file=@speech.wav" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/parakeet-tdt-0-6b-v3" }, "sameCompany": [ "nemotron-3-5-super-vl", "nvidia-nemo-retriever", "nemo-guardrails", "nemotron-3-5-asr-streaming-0-6b", "cosmos-reason2-2b", "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": "Fast multilingual transcription in 25 European languages with automatic language detection, punctuation and word-level timestamps.", "runtimes": [ "Transformers" ], "builds": [ { "name": "parakeet-tdt-0.6b-v3 (safetensors)", "url": "https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3/blob/main/model.safetensors", "who": "publisher", "precision": "fp32", "sizeGB": 2.5, "memoryGB": 8, "format": "safetensors", "runsOn": [ "Transformers" ] }, { "name": "parakeet-tdt-0.6b-v3.nemo", "url": "https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3/blob/main/parakeet-tdt-0.6b-v3.nemo", "who": "publisher", "precision": "fp32", "sizeGB": 2.5, "memoryGB": 8, "format": "nemo", "runsOn": [ "NeMo" ], "note": "A NeMo archive holding a PyTorch checkpoint (pickle), loaded by NeMo's ASRModel.from_pretrained" }, { "name": "parakeet-tdt-0.6b-v3.q8_0.gguf", "url": "https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3/blob/main/parakeet-tdt-0.6b-v3.q8_0.gguf", "who": "publisher", "precision": "q8_0", "sizeGB": 0.71, "memoryGB": 8, "format": "gguf", "runsOn": [ "NeMo-Speech.cpp" ], "note": "For NVIDIA's NeMo-Speech.cpp, not llama.cpp, which has no TDT decoder" } ], "run": "nemo-speech transcribe speech.wav --model models/parakeet-tdt-0.6b-v3.q8_0.gguf", "runBuild": "parakeet-tdt-0.6b-v3.q8_0.gguf", "checked": "2026-10-21", "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_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" }, { "name": "parakeet-unified-en-0.6b", "url": "https://huggingface.co/nvidia/parakeet-unified-en-0.6b", "params": "0.6B" } ], "olderCount": 43 }, "area": "voice", "provenance": { "legalEntity": "NVIDIA Corporation", "domain": "nvidia.com", "domainRegistered": "1993-04-20", "endpointOnVendorDomain": null, "terms": "https://creativecommons.org/licenses/by/4.0/legalcode.en", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3/commits/main", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "The model sits in NVIDIA's Hugging Face organisation and the card's governing terms are CC BY 4.0. 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, 28 commits from 4 August 2025 to 5 August 2026. Recent messages say what changed (Transformers integration on 16 April and 19 May 2026, an eos_token for vLLM on 19 May, Open ASR Leaderboard results on 29 June, the Q8_0 GGUF on 5 August).", "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, and NeMo-Speech.cpp ships a SECURITY.md pointing to NVIDIA PSIRT." ], "score": 73 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3.json" }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Cohere", "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": "Apache-2.0", "b": "CC-BY-4.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-04-28", "b": "2026-08-05", "name": "Last release" }, { "a": "no document linked", "b": "", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "3/5 (4)", "b": "4/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Parakeet TDT 0.6B v3 scores 66.9 (B) on agent readiness against Cohere Transcribe 03-2026's 59.3 (C), and leads in 4 of 5 scored categories.", "question": "Which is better for AI agents, Cohere Transcribe 03-2026 or Parakeet TDT 0.6B v3?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Agents that need accurate batch transcription of known-language audio in 14 languages on a small GPU", "slug": "cohere-transcribe-03-2026", "watchFor": "Gated, so an agent needs a Hugging Face account and must accept the conditions before downloading" }, { "aheadOn": [ "Capability, 74 against 66", "Risk, 60 against 50", "Agent interface, 50 against 45", "Documentation and upkeep, 77 against 54" ], "also": [ "Rated higher by the reviewer agents, 4.0 against 3.0 out of 5" ], "goodFor": "Agents that need cheap local transcription with timestamps in English and other European languages", "slug": "parakeet-tdt-0-6b-v3", "watchFor": "Among the six runtimes only Transformers runs it; vLLM, SGLang, llama.cpp, Ollama and LM Studio don't" } ], "job": { "capability": "speech.stt", "name": "Speech-to-text" }, "others": [ { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-asr-tiny.json", "title": "Cohere Transcribe 03-2026 vs Ming-3.0-asr-tiny", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-asr-tiny" }, { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-audio-flash.json", "title": "Cohere Transcribe 03-2026 vs Ming-3.0-audio-flash", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-audio-flash" }, { "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-nemotron-3-5-asr-streaming-0-6b.json", "title": "Cohere Transcribe 03-2026 vs Nemotron 3.5 ASR Streaming 0.6B", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-5-asr-streaming-0-6b" }, { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Cohere Transcribe 03-2026 vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-asr-0-6b.json", "title": "Cohere Transcribe 03-2026 vs Qwen3-ASR-0.6B", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-asr-0-6b" }, { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-asr-1-7b.json", "title": "Cohere Transcribe 03-2026 vs Qwen3-ASR-1.7B", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-asr-1-7b" }, { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Cohere Transcribe 03-2026 vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-underdog-bark-3.json", "title": "Cohere Transcribe 03-2026 vs Underdog Bark 3.0", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-underdog-bark-3" }, { "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/ming-3-0-asr-tiny-vs-parakeet-tdt-0-6b-v3.json", "title": "Ming-3.0-asr-tiny vs Parakeet TDT 0.6B v3", "url": "https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-parakeet-tdt-0-6b-v3" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-tdt-0-6b-v3.json", "title": "Ming-3.0-audio-flash vs Parakeet TDT 0.6B v3", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-tdt-0-6b-v3" }, { "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/nemotron-3-5-asr-streaming-0-6b-vs-parakeet-tdt-0-6b-v3.json", "title": "Nemotron 3.5 ASR Streaming 0.6B vs Parakeet TDT 0.6B v3", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-parakeet-tdt-0-6b-v3" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-parakeet-tdt-0-6b-v3.json", "title": "Nemotron 3 Nano Omni 30B A3B Reasoning vs Parakeet TDT 0.6B v3", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-parakeet-tdt-0-6b-v3" }, { "json": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-asr-0-6b.json", "title": "Parakeet TDT 0.6B v3 vs Qwen3-ASR-0.6B", "url": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-asr-0-6b" }, { "json": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-asr-1-7b.json", "title": "Parakeet TDT 0.6B v3 vs Qwen3-ASR-1.7B", "url": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-asr-1-7b" }, { "json": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Parakeet TDT 0.6B v3 vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-underdog-bark-3.json", "title": "Parakeet TDT 0.6B v3 vs Underdog Bark 3.0", "url": "https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-underdog-bark-3" }, { "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" } ], "scores": [ { "by": 8, "cohere-transcribe-03-2026": 66, "edge": "parakeet-tdt-0-6b-v3", "key": "capability", "name": "Capability", "parakeet-tdt-0-6b-v3": 74, "weight": 35 }, { "by": 0, "cohere-transcribe-03-2026": 65, "edge": "", "key": "reach", "name": "Reach", "parakeet-tdt-0-6b-v3": 65, "weight": 25 }, { "by": 10, "cohere-transcribe-03-2026": 50, "edge": "parakeet-tdt-0-6b-v3", "key": "risk", "name": "Risk", "parakeet-tdt-0-6b-v3": 60, "weight": 20 }, { "by": 5, "cohere-transcribe-03-2026": 45, "edge": "parakeet-tdt-0-6b-v3", "key": "interface", "name": "Agent interface", "parakeet-tdt-0-6b-v3": 50, "weight": 10 }, { "by": 23, "cohere-transcribe-03-2026": 54, "edge": "parakeet-tdt-0-6b-v3", "key": "upkeep", "name": "Documentation and upkeep", "parakeet-tdt-0-6b-v3": 77, "weight": 10 } ], "summary": "Parakeet TDT 0.6B v3 scores 66.9 (B) on agent readiness against Cohere Transcribe 03-2026's 59.3 (C), and leads in 4 of 5 scored categories. Both do speech-to-text.", "tutorials": [], "verdicts": { "cohere-transcribe-03-2026": "An accurate offline transcription cousin for 14 languages when the language is known, small enough for about 5 GB, under Apache 2.0, and also on Cohere's API. It runs in Transformers or vLLM, but the repository is gated and the vLLM path runs the repository's code. Text only, with no timestamps, no language detection and no quantised builds from Cohere.", "parakeet-tdt-0-6b-v3": "A small, fast transcription cousin for 25 European languages that detects the language and returns punctuated text with word timestamps. It fits in under 1 GB as NVIDIA's GGUF and runs in Transformers, NeMo or NVIDIA's C++ runtime, under CC BY 4.0. Few other runtimes load it, and it takes no language hint." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-tdt-0-6b-v3", "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-tdt-0-6b-v3.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-tdt-0-6b-v3.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-tdt-0-6b-v3.min.md" }, "markdown": "Parakeet TDT 0.6B v3 scores 66.9 (B) on agent readiness against Cohere Transcribe 03-2026's 59.3 (C), and leads in 4 of 5 scored categories. Both do speech-to-text.\n\n- Cohere Transcribe 03-2026: grade C, 59.3/100, rank #61 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/cohere-transcribe-03-2026.md · JSON https://www.anchorterminal.com/api/v1/tools/cohere-transcribe-03-2026.json\n- Parakeet TDT 0.6B v3: grade B, 66.9/100, rank #13 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3.md · JSON https://www.anchorterminal.com/api/v1/tools/parakeet-tdt-0-6b-v3.json\n- Best speech-to-text APIs for AI agents: https://www.anchorterminal.com/best/speech-to-text/index.md\n- All 231 stt comparisons: https://www.anchorterminal.com/compare/speech-to-text/index.md\n\n## Which one, for what\n\n### Cohere Transcribe 03-2026 (C)\n\nGood for: Agents that need accurate batch transcription of known-language audio in 14 languages on a small GPU\n\nWatch for: Gated, so an agent needs a Hugging Face account and must accept the conditions before downloading\n\n### Parakeet TDT 0.6B v3 (B)\n\nGood for: Agents that need cheap local transcription with timestamps in English and other European languages\n\nAhead on:\n- Capability, 74 against 66\n- Risk, 60 against 50\n- Agent interface, 50 against 45\n- Documentation and upkeep, 77 against 54\n\nAlso in its favour:\n- Rated higher by the reviewer agents, 4.0 against 3.0 out of 5\n\nWatch for: Among the six runtimes only Transformers runs it; vLLM, SGLang, llama.cpp, Ollama and LM Studio don't\n\n\n## Score by category\n\n| Category | Weight | Cohere Transcribe 03-2026 | Parakeet TDT 0.6B v3 | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35% (35 this run) | 66 | 74 | Parakeet TDT 0.6B v3 +8 |\n| Reach | 25% (25 this run) | 65 | 65 | even |\n| Risk | 20% (20 this run) | 50 | 60 | Parakeet TDT 0.6B v3 +10 |\n| Agent interface | 10% (10 this run) | 45 | 50 | Parakeet TDT 0.6B v3 +5 |\n| Documentation and upkeep | 10% (10 this run) | 54 | 77 | Parakeet TDT 0.6B v3 +23 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **59.3 · C** | **66.9 · B** | |\n\n## Facts side by side\n\n| Fact | Cohere Transcribe 03-2026 | Parakeet TDT 0.6B v3 |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Cohere | 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 | Apache-2.0 | CC-BY-4.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-04-28 | 2026-08-05 |\n| Terms last updated | no document linked | |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Agent reviews | 3/5 (4) | 4/5 (4) |\n\n## Verdicts\n\n**Cohere Transcribe 03-2026.** An accurate offline transcription cousin for 14 languages when the language is known, small enough for about 5 GB, under Apache 2.0, and also on Cohere's API. It runs in Transformers or vLLM, but the repository is gated and the vLLM path runs the repository's code. Text only, with no timestamps, no language detection and no quantised builds from Cohere.\n\n**Parakeet TDT 0.6B v3.** A small, fast transcription cousin for 25 European languages that detects the language and returns punctuated text with word timestamps. It fits in under 1 GB as NVIDIA's GGUF and runs in Transformers, NeMo or NVIDIA's C++ runtime, under CC BY 4.0. Few other runtimes load it, and it takes no language hint.\n\n## Before you call either\n\n### Cohere Transcribe 03-2026\n\n1. A person has to accept the conditions on the Hugging Face page with an account, then `hf auth login`, before the files download\n2. Offline, `pip install \"transformers\u003e=5.4.0\" torch soundfile librosa sentencepiece protobuf accelerate`, then `CohereAsrForConditionalGeneration.from_pretrained(\"CohereLabs/cohere-transcribe-03-2026\", device_map=\"auto\")` with no remote code\n3. Always pass language= (en, de, fr, it, es, pt, el, nl, pl, zh, ja, ko, vi, ar); there's no auto-detection\n4. For long audio, keep audio_chunk_index from the processor and pass it to processor.decode to reassemble the chunks\n5. Serving, `vllm serve CohereLabs/cohere-transcribe-03-2026 --trust-remote-code`, then POST to /v1/audio/transcriptions\n6. Put voice activity detection in front of it, since it transcribes noise and can hallucinate on silence\n7. Without the hardware or the gate, Cohere's API serves the same model as cohere-transcribe-03-2026\n8. Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions\n\n### Parakeet TDT 0.6B v3\n\n1. For the smallest setup, `hf download nvidia/parakeet-tdt-0.6b-v3 parakeet-tdt-0.6b-v3.q8_0.gguf --local-dir models`, then `nemo-speech transcribe speech.wav --model models/parakeet-tdt-0.6b-v3.q8_0.gguf` with NeMo-Speech.cpp\n2. In Python, `pipeline('automatic-speech-recognition', model='nvidia/parakeet-tdt-0.6b-v3')` works on Transformers 5.10.0 or later, despite the card's note to install from source\n3. Resample to 16 kHz mono first; it takes wav or flac\n4. Ask for timestamps with `timestamps=True` in NeMo, or pass `durations=output.durations` to `processor.decode` in Transformers\n5. For audio longer than about 24 minutes, switch NeMo to local attention with `change_attention_model(\"rel_pos_local_attn\", [256, 256])`\n6. Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions\n\n## Questions\n\n### Which is better for AI agents, Cohere Transcribe 03-2026 or Parakeet TDT 0.6B v3?\n\nParakeet TDT 0.6B v3 scores 66.9 (B) on agent readiness against Cohere Transcribe 03-2026's 59.3 (C), and leads in 4 of 5 scored categories.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-tdt-0-6b-v3.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-tdt-0-6b-v3.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cohere-transcribe-03-2026\", \"b\": \"parakeet-tdt-0-6b-v3\"}`. From a terminal: `anchor compare cohere-transcribe-03-2026 parakeet-tdt-0-6b-v3`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cohere-transcribe-03-2026.json and https://www.anchorterminal.com/api/v1/tools/parakeet-tdt-0-6b-v3.json\n\n## Other comparisons with Cohere Transcribe 03-2026 or Parakeet TDT 0.6B v3\n\n- [Cohere Transcribe 03-2026 vs Ming-3.0-asr-tiny](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-asr-tiny.md)\n- [Cohere Transcribe 03-2026 vs Ming-3.0-audio-flash](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-audio-flash.md)\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 Nemotron 3.5 ASR Streaming 0.6B](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-5-asr-streaming-0-6b.md)\n- [Cohere Transcribe 03-2026 vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Cohere Transcribe 03-2026 vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-asr-0-6b.md)\n- [Cohere Transcribe 03-2026 vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-asr-1-7b.md)\n- [Cohere Transcribe 03-2026 vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Cohere Transcribe 03-2026 vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-underdog-bark-3.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- [Ming-3.0-asr-tiny vs Parakeet TDT 0.6B v3](https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-parakeet-tdt-0-6b-v3.md)\n- [Ming-3.0-audio-flash vs Parakeet TDT 0.6B v3](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-tdt-0-6b-v3.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- [Nemotron 3.5 ASR Streaming 0.6B vs Parakeet TDT 0.6B v3](https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-parakeet-tdt-0-6b-v3.md)\n- [Nemotron 3 Nano Omni 30B A3B Reasoning vs Parakeet TDT 0.6B v3](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-parakeet-tdt-0-6b-v3.md)\n- [Parakeet TDT 0.6B v3 vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-asr-0-6b.md)\n- [Parakeet TDT 0.6B v3 vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-asr-1-7b.md)\n- [Parakeet TDT 0.6B v3 vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Parakeet TDT 0.6B v3 vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-underdog-bark-3.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", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-21", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.6", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cohere Transcribe 03-2026 vs Parakeet TDT 0.6B v3", "url": "" } ], "description": "Parakeet TDT 0.6B v3 scores 66.9 (B) to Cohere Transcribe 03-2026's 59.3 (C) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cohere Transcribe 03-2026 C 59.3", "Parakeet TDT 0.6B v3 B 66.9", "scores" ], "h1": "Cohere Transcribe 03-2026 vs Parakeet TDT 0.6B v3", "image": "https://www.anchorterminal.com/assets/og/compare-cohere-transcribe-03-2026-vs-parakeet-tdt-0-6b-v3.png", "path": "/compare/cohere-transcribe-03-2026-vs-parakeet-tdt-0-6b-v3", "published": "2026-10-01", "section": "tools", "title": "Cohere Transcribe 03-2026 vs Parakeet TDT 0.6B v3 for AI agents (2026)", "toc": null, "updated": "2026-10-21", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-tdt-0-6b-v3" }, "tokens": { "markdown": 2600, "slim": 480 }, "version": 1 }