{ "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", "dns": "cohere-transcribe-03-2026.grade.anchorterminal.com", "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": 60.3, "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": 1518, "categoryRank": 21, "methodology": "0.7", "run": "2026-10-01", "scores": { "capability": 66, "interface": 45, "reach": 65, "risk": 50, "upkeep": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": 0, "verdict": "An offline transcription model 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 Cohere replies to repository questions 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": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.3 } ], "editorialScores": { "capability": 66, "interface": 45, "reach": 65, "risk": 50, "upkeep": 64 }, "provenanceScore": 75, "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": "# 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", "north-mini-code-1-0" ], "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": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cohere-transcribe-03-2026.json", "live": { "slug": "cohere-transcribe-03-2026", "securityTxt": { "url": "https://cohere.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-10T16:07:22.890424476Z" }, "llmsTxt": { "url": "https://docs.cohere.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-10T15:42:46.623570536Z" }, "domain": { "domain": "cohere.com", "registered": "2000-03-07", "source": "https://rdap.verisign.com/com/v1/domain/cohere.com", "checkedAt": "2026-11-08T15:00:18.417824779Z" }, "pages": [ { "url": "https://docs.cohere.com/changelog/cohere-transcribe-03-2026", "kind": "changelog", "status": 200, "checkedAt": "2026-11-10T16:16:18.122178549Z", "changedAt": "2026-10-28T04:14:29.793599186Z", "fingerprint": "4c9113550b0b" } ], "updatedAt": "2026-11-10T16:16:18.122178549Z" } }, "answer": "Granite Speech 5.0 2B and Cohere Transcribe 03-2026 score within a point of each other on agent readiness, 61 (C) and 60.3 (C).", "b": { "slug": "granite-speech-5-0-2b", "name": "Granite Speech 5.0 2B", "vendor": "IBM", "vendorUrl": "https://www.ibm.com/granite", "kind": "weights", "category": "speech-to-text", "summary": "Granite Speech 5.0 2B is IBM's open-weight speech model of 2.3B parameters for transcription in six languages and speech translation to and from English, with keyword lists. Apache 2.0, with IBM's own GGUF builds from about 2 GB.", "url": "https://www.anchorterminal.com/tools/granite-speech-5-0-2b", "markdownUrl": "https://www.anchorterminal.com/tools/granite-speech-5-0-2b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/granite-speech-5-0-2b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/granite-speech-5-0-2b.json", "dns": "granite-speech-5-0-2b.grade.anchorterminal.com", "repo": "https://huggingface.co/ibm-granite/granite-speech-5.0-2b", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "ibm-granite/granite-speech-5.0-2b" }, { "registry": "huggingface", "name": "ibm-granite/granite-speech-5.0-2b-GGUF" }, { "registry": "ollama", "name": "ibm/granite5-speech" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The safetensors and GGUF repositories are not gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download and use under Apache 2.0. Running it yourself costs little: 3.1 GB at Q8_0 with its audio projector, which IBM recommends, or 5.0 GB in BF16. IBM also runs a trial endpoint on Hugging Face that takes a Hugging Face token (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/ibm-granite/granite-speech-5.0-2b", "capabilities": [ "speech.stt", "speech.batch", "speech.languages", "speech.translation", "model.open-weights" ], "tags": [ "open-weights", "model", "speech-to-text", "asr", "speech-translation", "multilingual", "keyword-biasing", "small", "apache-2.0", "safetensors", "gguf", "signed", "self-hosted" ], "lastRelease": "2026-11-06", "graded": true, "anchor": { "graded": true, "score": 61, "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": 1518, "categoryRank": 19, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 55, "reach": 95, "risk": 70, "upkeep": 92 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-10" }, "negative": 0, "verdict": "A small, well-kept speech model with a clean licence: six languages, translation, keyword lists, IBM's own GGUF and an Ollama entry, a signed repository and training data listed corpus by corpus. It handles about two minutes of audio at a time and returns plain text, with no timestamps or speakers, and publishes no safety results.", "bestFor": "Agents that need to transcribe or translate short recordings in the six supported languages on modest hardware", "strengths": [ "Apache 2.0, ungated, with a signed repository", "Runs in llama.cpp, Ollama, vLLM and Transformers, each documented", "IBM's own GGUF builds, about 3 GB at the precision it recommends", "Training data listed with hours and sources", "Keyword lists of up to 2,000 terms", "Updated in the last week, and both questions on the repository answered" ], "weaknesses": [ "About two minutes of audio per request, so long recordings must be split", "Plain text out: no timestamps, segments or speaker labels", "Six languages", "Builds below Q8_0 lose accuracy on longer audio, by IBM's own account", "No safety results", "No cut-off for the training data" ], "agentNotes": [ "Split recordings into segments of up to about two minutes of 16 kHz mono audio before sending them", "Use the card's prompt for the task word for word, such as `transcribe the speech with proper punctuation and capitalization.`", "Use Q8_0. IBM says lower precisions lose accuracy on audio over about a minute", "To spell names and jargon right, add a keyword list to the prompt, up to 2,000 terms", "With vLLM, serve with `--max-model-len 2048`, as the card does", "An unknown prompt falls back to transcription, so check that the output is the task you asked for" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 55, "reach": 95, "risk": 70, "upkeep": 92 }, "provenanceScore": 88, "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": "brew install llama.cpp\nllama-cli -st -hf ibm-granite/granite-speech-5.0-2b-GGUF:Q8_0 --audio audio.wav -p \"transcribe the speech with proper punctuation and capitalization.\"\n# or: ollama run ibm/granite5-speech:2b, or vllm serve ibm-granite/granite-speech-5.0-2b --max-model-len 2048", "http": "# vLLM and llama-server both serve an OpenAI-compatible chat API. Send 16 kHz mono audio of up to about\n# two minutes as base64 in the message, with one of the card's task prompts as the text" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/granite-speech-5-0-2b" }, "sameCompany": [ "granite-embedding-small-english-r2", "granite-guardian", "ibm-watson-stt", "granite-switch", "granite-4-2-30b", "granite-4-2-3b", "granite-4-2-8b" ], "weights": { "trainedBy": "IBM", "builtOn": "An intermediate checkpoint of granite-4.0-1b-base, per the card", "params": "2.3B", "goodFor": "Transcribing and translating short recordings in six languages on a laptop, with a keyword list for names and jargon.", "runtimes": [ "llama.cpp", "Ollama", "vLLM", "Transformers" ], "builds": [ { "name": "granite-speech-5.0-2b-GGUF Q4_K_M", "url": "https://huggingface.co/ibm-granite/granite-speech-5.0-2b-GGUF/blob/main/granite-speech-5.0-2b-Q4_K_M.gguf", "who": "publisher", "precision": "q4_k_m", "sizeGB": 2.3, "memoryGB": 8, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "1.14 GB with the 1.16 GB audio projector. IBM says precisions below Q8_0 lose accuracy on audio over about a minute" }, { "name": "granite-speech-5.0-2b-GGUF Q8_0", "url": "https://huggingface.co/ibm-granite/granite-speech-5.0-2b-GGUF/blob/main/granite-speech-5.0-2b-Q8_0.gguf", "who": "publisher", "precision": "q8_0", "sizeGB": 3.12, "memoryGB": 8, "format": "gguf", "runsOn": [ "llama.cpp", "Ollama" ], "note": "1.96 GB with the 1.16 GB audio projector. The build IBM recommends, and the one in Ollama's library" }, { "name": "granite-speech-5.0-2b (BF16 safetensors)", "url": "https://huggingface.co/ibm-granite/granite-speech-5.0-2b/tree/main", "who": "publisher", "precision": "bf16", "sizeGB": 5.04, "memoryGB": 8, "format": "safetensors", "runsOn": [ "vLLM", "Transformers" ], "note": "Two shards" } ], "run": "llama-cli -st -hf ibm-granite/granite-speech-5.0-2b-GGUF:Q8_0 --audio audio.wav -p \"transcribe the speech with proper punctuation and capitalization.\"", "runBuild": "granite-speech-5.0-2b-GGUF Q8_0", "checked": "2026-11-10", "minMemoryGB": 8 }, "family": { "lab": "IBM (Granite)", "family": "Granite Speech", "url": "https://www.anchorterminal.com/open-weights/#ibm", "others": [ { "name": "granite-speech-5.0-470m-turboctc", "url": "https://huggingface.co/ibm-granite/granite-speech-5.0-470m-turboctc", "params": "470M, per the name" }, { "name": "granite-speech-4.1-2b", "url": "https://huggingface.co/ibm-granite/granite-speech-4.1-2b", "params": "2B, per the name" } ], "olderCount": 64 }, "area": "voice", "provenance": { "legalEntity": "International Business Machines Corporation (per IBM's naming guidance, as read for granite-guardian)", "domain": "ibm.com", "domainRegistered": "1986-03-19", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/ibm-granite/granite-speech-5.0-2b/commits/main", "securityTxt": "valid", "checked": "2026-11-10", "notes": [ "IBM's legal entity, domain and security.txt are carried from our Granite 4.2 listings.", "Nothing is hosted under this listing, so Apache 2.0 stands in for terms of service and no privacy policy is scored.", "The changelog is the commit history, 28 commits from 7 October to 6 November 2026.", "The card gives 20 October 2026 as the release date." ], "score": 88 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/granite-speech-5-0-2b.json" }, "edges": [ { "by": 30, "category": "reach", "leads": "granite-speech-5-0-2b", "name": "Reach", "reasons": { "a": "Memory earns 30, since the BF16 file is 4.13 GB and needs about 5 GB. Runtimes get 10 for Transformers (v5.4.0 to v5.22.1) and vLLM (v0.32.0 and v0.33.0), both released; llama.cpp, SGLang, Ollama and LM Studio don't run it. Builds score 0, as Cohere publishes no quantised build. Apache 2.0 with nothing added gives terms 15. Download gets 5 because the repository is a click-through gate that needs an account. Hosted too gets 5 for Cohere's own API and fal.", "b": "Memory 30, the smallest build listed that keeps 4 bits is IBM's Q4_K_M GGUF, 1.14 GB with the 1.16 GB audio projector, and 2.30 GB × 1.2 = 2.8 GB, within 16 GB. IBM recommends Q8_0, 3.12 GB with the projector. Runtimes 20, Released Transformers 5.22.2 and vLLM 0.33.0 have the granite_speech model, llama.cpp b12242 has its converter and audio front end, and Ollama carries it as ibm/granite5-speech, which the card says was tested with v0.40.15. Builds 15, IBM publishes GGUF builds at fourteen quantised precisions, from Q2_K to Q8_0, with the audio projector. Terms 15, Apache 2.0 in the metadata and on the card, with nothing added. Download 10, the Hub API reports gated false for both repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, IBM runs a Hugging Face Inference Endpoint that serves this model through an OpenAI-compatible API, with the address and code on the card. 30 + 20 + 15 + 15 + 10 + 5 = 95." }, "scores": { "a": 65, "b": 95 } }, { "by": 28, "category": "upkeep", "leads": "granite-speech-5-0-2b", "name": "Documentation and upkeep", "reasons": { "a": "The public card covers intended use, limitations, architecture, parameters and languages, without a context length or cut-off (14). Training data has a size and method but no sources or cut-off (5). The last change is the card commit of 7 October 2026 (pull request 49, which adds runtime and app support notes), 28 days before 4 November; card and documentation commits count on this line in this re-check, as for other open-weight listings (20; 10 before, on the 28 April configuration file). Cohere answered 11 of 23 questions, none since April (10). It's a first release with a dated name (5), and every report of a broken file has a reply (10). 14 + 5 + 20 + 10 + 5 + 10 = 64.", "b": "Model card 17, Intended use, limitations, the architecture, the size, the 16K positions and two-minute segments, and the languages are on the card. Training data 20, the data is listed with sources and sizes: a 39-row table giving each corpus, its task, its hours and a link to where it comes from, with the synthetic sets described. Last change 20, the last commit, on 6 November 2026, updated the card, 4 days before this check. Responsiveness 20, Both discussions that aren't pull requests (21 and 28 October 2026) have a reply from an ibm-granite member. Version policy 5, granite-speech-4.1-2b stays in its own repository and 5.0 came out in a new one, which names its predecessor and gives a release date. File health 10, Config, template and card agree on the architecture and the 16K positions. 17 + 20 + 20 + 20 + 5 + 10 = 92." }, "scores": { "a": 64, "b": 92 } }, { "by": 20, "category": "risk", "leads": "granite-speech-5-0-2b", "name": "Risk", "reasons": { "a": "File safety gets 15, safetensors only but served in vLLM with --trust-remote-code as the card documents. Provenance gets 10 for Cohere's verified organisation; the checksums are hidden behind the gate and weren't seen. Licence risk keeps 15 under Apache 2.0. Agent guidance gets 5 for cautions about hallucinating on noise. The security programme gets 5 for Cohere's disclosure policy and bug bounty, with no security.txt and no public advisories. Safety evaluation scores 0.", "b": "File safety 25, safetensors and GGUF only, no .bin, .pt or .pth files and no Python in either repository. Provenance 15, the files sit in the ibm-granite organisation, which IBM's Granite docs link to (10). Safety evaluation 0, no safety results on the card. Agent guidance 10, the card says what the model does with a prompt it doesn't know: it ignores an unfamiliar or malformed prompt and transcribes, which it says limits how audio can steer the system. Licence risk 15, Apache 2.0 with no use policy, no threshold and no right to change the terms. Security programme 5, www.ibm.com/.well-known/security.txt names IBM PSIRT, read for the Granite 4.2 3B listing on 4 November 2026 (5). 25 + 15 + 0 + 10 + 15 + 5 = 70." }, "scores": { "a": 50, "b": 70 } }, { "by": 10, "category": "interface", "leads": "granite-speech-5-0-2b", "name": "Agent interface", "reasons": { "a": "Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. Cohere documents the audio, language and punctuation inputs and the decoded text with chunk reassembly in Transformers, and the vLLM transcription request (25). It was trained for one stated language per clip (10). There are no timestamps, segments or documented JSON (0). The chat template line gets 10 because the prompt is built by the processor. Reasoning control and context score 0, with no reasoning and no stated context.", "b": "Chat template 20, chat_template.jinja in the repository (193 characters). 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 model with no reasoning. Context 0, the language model is extended to 16K positions, per the card and config.json (16,384), below the 32K band, and the card says to send audio in segments of about two minutes. 20 + 25 + 10 + 0 + 0 + 0 = 55." }, "scores": { "a": 45, "b": 55 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Cohere", "b": "IBM", "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": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-04-28", "b": "2026-11-06", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Granite Speech 5.0 2B and Cohere Transcribe 03-2026 score within a point of each other on agent readiness, 61 (C) and 60.3 (C).", "question": "Which is better for AI agents, Cohere Transcribe 03-2026 or Granite Speech 5.0 2B?" } ], "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": [ "Reach, 95 against 65", "Risk, 70 against 50", "Agent interface, 55 against 45", "Documentation and upkeep, 92 against 64" ], "also": null, "goodFor": "Agents that need to transcribe or translate short recordings in the six supported languages on modest hardware", "slug": "granite-speech-5-0-2b", "watchFor": "About two minutes of audio per request, so long recordings must be split" } ], "history": { "cohere-transcribe-03-2026": [ { "causes": [ "correction" ], "date": "2026-11-04", "delta": 1, "from": 59.3, "fromGrade": "C", "to": 60.3, "toGrade": "C" } ], "granite-speech-5-0-2b": null }, "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-3-5-transcribe-30b-a4b.json", "title": "Cohere Transcribe 03-2026 vs Nemotron 3.5 Transcribe 30B-A4B", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-5-transcribe-30b-a4b" }, { "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-parakeet-tdt-0-6b-v3.json", "title": "Cohere Transcribe 03-2026 vs Parakeet TDT 0.6B v3", "url": "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-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-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/granite-speech-5-0-2b-vs-ming-3-0-asr-tiny.json", "title": "Granite Speech 5.0 2B vs Ming-3.0-asr-tiny", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-asr-tiny" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-flash.json", "title": "Granite Speech 5.0 2B vs Ming-3.0-audio-flash", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-flash" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-tiny.json", "title": "Granite Speech 5.0 2B vs Ming-3.0-audio-tiny", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-tiny" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-5-asr-streaming-0-6b.json", "title": "Granite Speech 5.0 2B vs Nemotron 3.5 ASR Streaming 0.6B", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-5-asr-streaming-0-6b" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-5-transcribe-30b-a4b.json", "title": "Granite Speech 5.0 2B vs Nemotron 3.5 Transcribe 30B-A4B", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-5-transcribe-30b-a4b" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Granite Speech 5.0 2B vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-parakeet-tdt-0-6b-v3.json", "title": "Granite Speech 5.0 2B vs Parakeet TDT 0.6B v3", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-parakeet-tdt-0-6b-v3" }, { "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-qwen3-asr-0-6b.json", "title": "Granite Speech 5.0 2B vs Qwen3-ASR-0.6B", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-qwen3-asr-0-6b" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-qwen3-asr-1-7b.json", "title": "Granite Speech 5.0 2B vs Qwen3-ASR-1.7B", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-qwen3-asr-1-7b" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Granite Speech 5.0 2B vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-underdog-bark-3.json", "title": "Granite Speech 5.0 2B vs Underdog Bark 3.0", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-underdog-bark-3" }, { "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" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 30, "cohere-transcribe-03-2026": 65, "edge": "granite-speech-5-0-2b", "granite-speech-5-0-2b": 95, "key": "reach", "name": "Reach", "weight": 25 }, { "by": 20, "cohere-transcribe-03-2026": 50, "edge": "granite-speech-5-0-2b", "granite-speech-5-0-2b": 70, "key": "risk", "name": "Risk", "weight": 20 }, { "by": 10, "cohere-transcribe-03-2026": 45, "edge": "granite-speech-5-0-2b", "granite-speech-5-0-2b": 55, "key": "interface", "name": "Agent interface", "weight": 10 }, { "by": 28, "cohere-transcribe-03-2026": 64, "edge": "granite-speech-5-0-2b", "granite-speech-5-0-2b": 92, "key": "upkeep", "name": "Documentation and upkeep", "weight": 10 } ], "summary": "Granite Speech 5.0 2B and Cohere Transcribe 03-2026 score within a point of each other on agent readiness, 61 (C) and 60.3 (C). Both do speech-to-text.", "tasks": null, "tutorials": [], "verdicts": { "cohere-transcribe-03-2026": "An offline transcription model 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.", "granite-speech-5-0-2b": "A small, well-kept speech model with a clean licence: six languages, translation, keyword lists, IBM's own GGUF and an Ollama entry, a signed repository and training data listed corpus by corpus. It handles about two minutes of audio at a time and returns plain text, with no timestamps or speakers, and publishes no safety results." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-granite-speech-5-0-2b", "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-granite-speech-5-0-2b.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-granite-speech-5-0-2b.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-granite-speech-5-0-2b.min.md" }, "markdown": "Granite Speech 5.0 2B and Cohere Transcribe 03-2026 score within a point of each other on agent readiness, 61 (C) and 60.3 (C). Both do speech-to-text.\n\n- Cohere Transcribe 03-2026: grade C, 60.3/100, rank #89 of 160 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- Granite Speech 5.0 2B: grade C, 61/100, rank #67 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/granite-speech-5-0-2b.md · JSON https://www.anchorterminal.com/api/v1/tools/granite-speech-5-0-2b.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### 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### Granite Speech 5.0 2B (C)\n\nGood for: Agents that need to transcribe or translate short recordings in the six supported languages on modest hardware\n\nAhead on:\n- Reach, 95 against 65\n- Risk, 70 against 50\n- Agent interface, 55 against 45\n- Documentation and upkeep, 92 against 64\n\nWatch for: About two minutes of audio per request, so long recordings must be split\n\n\n## Why the edge\n\n### Reach: Granite Speech 5.0 2B +30\n\n- Cohere Transcribe 03-2026 (65): Memory earns 30, since the BF16 file is 4.13 GB and needs about 5 GB. Runtimes get 10 for Transformers (v5.4.0 to v5.22.1) and vLLM (v0.32.0 and v0.33.0), both released; llama.cpp, SGLang, Ollama and LM Studio don't run it. Builds score 0, as Cohere publishes no quantised build. Apache 2.0 with nothing added gives terms 15. Download gets 5 because the repository is a click-through gate that needs an account. Hosted too gets 5 for Cohere's own API and fal.\n- Granite Speech 5.0 2B (95): Memory 30, the smallest build listed that keeps 4 bits is IBM's Q4_K_M GGUF, 1.14 GB with the 1.16 GB audio projector, and 2.30 GB × 1.2 = 2.8 GB, within 16 GB. IBM recommends Q8_0, 3.12 GB with the projector. Runtimes 20, Released Transformers 5.22.2 and vLLM 0.33.0 have the granite_speech model, llama.cpp b12242 has its converter and audio front end, and Ollama carries it as ibm/granite5-speech, which the card says was tested with v0.40.15. Builds 15, IBM publishes GGUF builds at fourteen quantised precisions, from Q2_K to Q8_0, with the audio projector. Terms 15, Apache 2.0 in the metadata and on the card, with nothing added. Download 10, the Hub API reports gated false for both repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, IBM runs a Hugging Face Inference Endpoint that serves this model through an OpenAI-compatible API, with the address and code on the card. 30 + 20 + 15 + 15 + 10 + 5 = 95.\n\n### Documentation and upkeep: Granite Speech 5.0 2B +28\n\n- Cohere Transcribe 03-2026 (64): The public card covers intended use, limitations, architecture, parameters and languages, without a context length or cut-off (14). Training data has a size and method but no sources or cut-off (5). The last change is the card commit of 7 October 2026 (pull request 49, which adds runtime and app support notes), 28 days before 4 November; card and documentation commits count on this line in this re-check, as for other open-weight listings (20; 10 before, on the 28 April configuration file). Cohere answered 11 of 23 questions, none since April (10). It's a first release with a dated name (5), and every report of a broken file has a reply (10). 14 + 5 + 20 + 10 + 5 + 10 = 64.\n- Granite Speech 5.0 2B (92): Model card 17, Intended use, limitations, the architecture, the size, the 16K positions and two-minute segments, and the languages are on the card. Training data 20, the data is listed with sources and sizes: a 39-row table giving each corpus, its task, its hours and a link to where it comes from, with the synthetic sets described. Last change 20, the last commit, on 6 November 2026, updated the card, 4 days before this check. Responsiveness 20, Both discussions that aren't pull requests (21 and 28 October 2026) have a reply from an ibm-granite member. Version policy 5, granite-speech-4.1-2b stays in its own repository and 5.0 came out in a new one, which names its predecessor and gives a release date. File health 10, Config, template and card agree on the architecture and the 16K positions. 17 + 20 + 20 + 20 + 5 + 10 = 92.\n\n### Risk: Granite Speech 5.0 2B +20\n\n- Cohere Transcribe 03-2026 (50): File safety gets 15, safetensors only but served in vLLM with --trust-remote-code as the card documents. Provenance gets 10 for Cohere's verified organisation; the checksums are hidden behind the gate and weren't seen. Licence risk keeps 15 under Apache 2.0. Agent guidance gets 5 for cautions about hallucinating on noise. The security programme gets 5 for Cohere's disclosure policy and bug bounty, with no security.txt and no public advisories. Safety evaluation scores 0.\n- Granite Speech 5.0 2B (70): File safety 25, safetensors and GGUF only, no .bin, .pt or .pth files and no Python in either repository. Provenance 15, the files sit in the ibm-granite organisation, which IBM's Granite docs link to (10). Safety evaluation 0, no safety results on the card. Agent guidance 10, the card says what the model does with a prompt it doesn't know: it ignores an unfamiliar or malformed prompt and transcribes, which it says limits how audio can steer the system. Licence risk 15, Apache 2.0 with no use policy, no threshold and no right to change the terms. Security programme 5, www.ibm.com/.well-known/security.txt names IBM PSIRT, read for the Granite 4.2 3B listing on 4 November 2026 (5). 25 + 15 + 0 + 10 + 15 + 5 = 70.\n\n### Agent interface: Granite Speech 5.0 2B +10\n\n- Cohere Transcribe 03-2026 (45): Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. Cohere documents the audio, language and punctuation inputs and the decoded text with chunk reassembly in Transformers, and the vLLM transcription request (25). It was trained for one stated language per clip (10). There are no timestamps, segments or documented JSON (0). The chat template line gets 10 because the prompt is built by the processor. Reasoning control and context score 0, with no reasoning and no stated context.\n- Granite Speech 5.0 2B (55): Chat template 20, chat_template.jinja in the repository (193 characters). 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 model with no reasoning. Context 0, the language model is extended to 16K positions, per the card and config.json (16,384), below the 32K band, and the card says to send audio in segments of about two minutes. 20 + 25 + 10 + 0 + 0 + 0 = 55.\n\n## Score by category\n\n| Category | Weight | Cohere Transcribe 03-2026 | Granite Speech 5.0 2B | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 65 | 95 | Granite Speech 5.0 2B +30 |\n| Risk | 20% (20 this run) | 50 | 70 | Granite Speech 5.0 2B +20 |\n| Agent interface | 10% (10 this run) | 45 | 55 | Granite Speech 5.0 2B +10 |\n| Documentation and upkeep | 10% (10 this run) | 64 | 92 | Granite Speech 5.0 2B +28 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **60.3 · C** | **61 · C** | |\n\n## Facts side by side\n\n| Fact | Cohere Transcribe 03-2026 | Granite Speech 5.0 2B |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Cohere | IBM |\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 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-04-28 | 2026-11-06 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Agent reviews | 3/5 (4) | none |\n\n## How the scores have moved\n\n### Cohere Transcribe 03-2026\n\n- +1.0 on 4 November 2026: correction\n\n### Granite Speech 5.0 2B\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Cohere Transcribe 03-2026.** An offline transcription model 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**Granite Speech 5.0 2B.** A small, well-kept speech model with a clean licence: six languages, translation, keyword lists, IBM's own GGUF and an Ollama entry, a signed repository and training data listed corpus by corpus. It handles about two minutes of audio at a time and returns plain text, with no timestamps or speakers, and publishes no safety results.\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### Granite Speech 5.0 2B\n\n1. Split recordings into segments of up to about two minutes of 16 kHz mono audio before sending them\n2. Use the card's prompt for the task word for word, such as `transcribe the speech with proper punctuation and capitalization.`\n3. Use Q8_0. IBM says lower precisions lose accuracy on audio over about a minute\n4. To spell names and jargon right, add a keyword list to the prompt, up to 2,000 terms\n5. With vLLM, serve with `--max-model-len 2048`, as the card does\n6. An unknown prompt falls back to transcription, so check that the output is the task you asked for\n\n## Questions\n\n### Which is better for AI agents, Cohere Transcribe 03-2026 or Granite Speech 5.0 2B?\n\nGranite Speech 5.0 2B and Cohere Transcribe 03-2026 score within a point of each other on agent readiness, 61 (C) and 60.3 (C).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-granite-speech-5-0-2b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-granite-speech-5-0-2b.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cohere-transcribe-03-2026\", \"b\": \"granite-speech-5-0-2b\"}`. From a terminal: `anchor compare cohere-transcribe-03-2026 granite-speech-5-0-2b`\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/granite-speech-5-0-2b.json\n\n## Other comparisons with Cohere Transcribe 03-2026 or Granite Speech 5.0 2B\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 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-5-transcribe-30b-a4b.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 Parakeet TDT 0.6B v3](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-tdt-0-6b-v3.md)\n- [Cohere Transcribe 03-2026 vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-parakeet-unified-en-0-6b.md)\n- [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- [Granite Speech 5.0 2B vs Ming-3.0-asr-tiny](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-asr-tiny.md)\n- [Granite Speech 5.0 2B vs Ming-3.0-audio-flash](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-flash.md)\n- [Granite Speech 5.0 2B vs Ming-3.0-audio-tiny](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-tiny.md)\n- [Granite Speech 5.0 2B vs Nemotron 3.5 ASR Streaming 0.6B](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-5-asr-streaming-0-6b.md)\n- [Granite Speech 5.0 2B vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-5-transcribe-30b-a4b.md)\n- [Granite Speech 5.0 2B vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Granite Speech 5.0 2B vs Parakeet TDT 0.6B v3](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-parakeet-tdt-0-6b-v3.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 Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-qwen3-asr-0-6b.md)\n- [Granite Speech 5.0 2B vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-qwen3-asr-1-7b.md)\n- [Granite Speech 5.0 2B vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Granite Speech 5.0 2B vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-underdog-bark-3.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", "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": "Cohere Transcribe 03-2026 vs Granite Speech 5.0 2B", "url": "" } ], "description": "Granite Speech 5.0 2B and Cohere Transcribe 03-2026 score within a point of each other for speech-to-text, 61 and 60.3 out of 100. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cohere Transcribe 03-2026 C 60.3", "Granite Speech 5.0 2B C 61", "scores" ], "h1": "Cohere Transcribe 03-2026 vs Granite Speech 5.0 2B", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cohere-transcribe-03-2026-vs-granite-speech-5-0-2b", "published": "2026-10-01", "section": "tools", "title": "Cohere Transcribe 03-2026 vs Granite Speech 5.0 2B (2026)", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-granite-speech-5-0-2b" }, "tokens": { "markdown": 4150, "slim": 780 }, "version": 1 }