{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/speech-to-text.self-hosted-local/",
    "json": "https://www.anchorterminal.com/niches/speech-to-text.self-hosted-local/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/speech-to-text.self-hosted-local/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/speech-to-text.self-hosted-local/index.min.md"
  },
  "markdown": "Two or three companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 2 | 4 | 120 | 10 | 8 |\n\n## What counts as done\n\nThe model loads from a released runtime (Transformers, vLLM, llama.cpp, MLX or similar) without trust_remote_code.\n\nMeasured, for our own tests: it transcribes a 10-minute file faster than real time on the stated hardware, and matches the published WER within 2 points on a public set.\n\nHow agents ask for it: transcribe this locally, nothing leaves the machine; run a speech model on my Mac or one GPU; cheap transcription for hundreds of hours\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **Parakeet TDT 0.6B v3 (NVIDIA Corporation)**: Transformers pipeline loads the safetensors without remote code; the Open ASR Leaderboard row (6.32 mean WER in the repository's eval file, 4.94 on the cleaned sets per a third party) is independent of NVIDIA.\n- **Qwen3-ASR-0.6B (Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check))**: vLLM 0.32 and Transformers 5.13 (-hf repository) load it without remote code; a third-party card quotes its leaderboard row at 5.16 average on the cleaned sets, but the publisher figure was not compared.\n- **Qwen3-ASR-1.7B (Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check))**: vLLM 0.32 and Transformers 5.13 (-hf repository) load it without remote code; the Open ASR Leaderboard README lists Qwen3-ASR-1.7B as an evaluated model but its row could not be read.\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Cohere Transcribe 03-2026 (Cohere Inc.)**: CohereAsrForConditionalGeneration loads in Transformers without remote code, but the Hugging Face repository is gated behind a human-accepted licence, and the vLLM recipe uses --trust-remote-code.\n- **Ming-3.0-asr-tiny (inclusionAI, Ant Group (named in the site footer of inclusion-ai.org; the LICENSE copyright line reads inclusionAI))**: Loads only with trust_remote_code in Transformers or SGLang-Omni main; the published WER is the publisher's own with no leaderboard row.\n- **Nemotron 3.5 ASR Streaming 0.6B (NVIDIA Corporation)**: Transformers 5.13 pipeline loads the safetensors without remote code; the GGUF needs NVIDIA's NeMo-Speech.cpp, and no independent WER reproduction was found.\n- **Underdog Bark 3.0 (Conway Research)**: No runtime reads model.bark without Conway's loader, and the card itself says the Bark rows are not on the Open ASR Leaderboard; accuracy rests on Conway's own runs.\n- **Voxtral Mini 4B Realtime 2602 (Mistral AI (RCS Paris 952 418 325))**: vLLM and Transformers 5.2 load it without remote code, but acc-22 could not reproduce the paper's WER (FLEURS EN 13.00 against 4.90) and acc-27 hit an outdated Transformers in the vLLM image.\n\n- not this job: Amazon Transcribe (Amazon Web Services, Inc.): A hosted AWS service with no weights; audio must go to AWS.\n- not this job: AssemblyAI Speech-to-Text (Universal) (AssemblyAI, Inc.): Hosted API only, no weights.\n- not this job: Azure AI Speech speech-to-text (Microsoft Corporation): Hosted Azure service; containers exist but are not open weights and still bill through Azure.\n- not this job: Cartesia Ink (Cartesia AI, Inc.): Hosted API only.\n- not this job: Deepgram Speech-to-Text (Nova-3, Flux) (Deepgram, Inc.): Self-hosted Deepgram is a licensed container, not open weights.\n- not this job: ElevenLabs Scribe Speech to Text API (Eleven Labs Inc.): Hosted API only.\n- not this job: Giggy Speech to Text (Giggy): Hosted API only.\n- not this job: Gladia Speech-to-Text API + MCP (Gladia SAS): Hosted API only.\n- not this job: Google Cloud Speech-to-Text (Google LLC): Hosted Google Cloud service.\n- not this job: Groq Speech-to-Text (Groq LLC): Hosted inference of OpenAI's Whisper; no weights from Groq.\n- not this job: IBM Watson Speech to Text (International Business Machines Corporation): IBM Cloud service; the on-premises Cloud Pak is licensed software, not open weights.\n- not this job: Inworld STT (Theai, Inc. dba Inworld AI): Hosted API only.\n- not this job: Ming-3.0-audio-flash (inclusionAI, Ant Group (named in the inclusion-ai.org footer; no registered company named)): Every loading path uses trust_remote_code or inclusionAI's forks, needs a multi-GPU server, and no independent WER exists.\n- not this job: Ming-3.0-audio-tiny (inclusionAI (Ant Group)): Needs trust_remote_code or SGLang-Omni main, no released runtime, and only the publisher's WER.\n- not this job: MiniMax Speech-to-Text (Nanonoble Pte. Ltd.): Hosted API only.\n- not this job: Mistral Voxtral Transcribe (Mistral AI (RCS Paris 952 418 325)): This listing is the hosted API; the open weights are listed separately as voxtral-mini-4b-realtime-2602.\n- not this job: OpenAI Speech to Text (OpenAI OpCo, LLC): Hosted API; OpenAI's open Whisper weights are not this listing.\n- not this job: Rev AI Speech-to-Text API (Rev.com, Inc.): Hosted API only.\n- not this job: Smallest.ai Pulse STT (Smallest, Inc.): Hosted API only.\n- not this job: Soniox Speech-to-Text (Soniox Inc.): Hosted API only.\n- not this job: Speechmatics Speech-to-Text (Cantab Research Ltd): Containers are licensed deployments, not open weights.\n\n3 listings in the category were added after this reading and aren't marked yet.\n\n## What stops agents finishing\n\n- no released runtime loads it (Ming, Nemotron GGUF needs NeMo-Speech.cpp, Underdog Bark needs the publisher's loader)\n- gated download needing a human to accept terms (Cohere Transcribe)\n- serving stack ships an old Transformers and the model will not start (acc-27)\n- generation cap set too low silently truncates (acc-22: max_new_tokens must be at least duration / 80 ms)\n- CUDA out of memory on long audio (Parakeet discussion #41)\n\n## Around it\n\nBefore: model.download-weights, audio.resample-16k. After: diarisation.pyannote, llm.summarise.\n\n## Where this comes from\n\nWeight 10 of 100 in Speech-to-text: 8 of 32 accounts ran open weights (acc-08, acc-12, acc-13, acc-17, acc-22, acc-25, acc-27, acc-32); counted here where the local run itself was the point\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/speech-to-text.self-hosted-local.json, or the MCP tool get_use_case with id speech-to-text.self-hosted-local. Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person.\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": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "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": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Transcribe on the user's own hardware without sending audio out",
        "url": ""
      }
    ],
    "description": "Transcribe on the user's own hardware without sending audio out: 2 companies fully do it, 4 with a limit, 120 carry the tag. Every listing in Speech-to-text with the reason and a source.",
    "facts": null,
    "h1": "Transcribe on the user's own hardware without sending audio out",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/speech-to-text.self-hosted-local/",
    "published": "",
    "section": "agents",
    "title": "Transcribe on the user's own hardware without sending audio out |…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/speech-to-text.self-hosted-local/"
  },
  "tokens": {
    "markdown": 1800,
    "slim": 330
  },
  "version": 1
}
