{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/speech-to-text.dictation-to-agent/",
    "json": "https://www.anchorterminal.com/niches/speech-to-text.dictation-to-agent/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/speech-to-text.dictation-to-agent/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/speech-to-text.dictation-to-agent/index.min.md"
  },
  "markdown": "Four or more 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| 8 | 17 | 42 | 10 | 4 |\n\n## What counts as done\n\nClean punctuated text back for a 30-second clip.\n\nMeasured, for our own tests: the text arrives within 2 seconds of the clip ending, with no filler text or hallucinated sentence on a clip that is partly silent.\n\nHow agents ask for it: transcribe this 20-second voice note; I'll speak my prompt, type it for me; turn this voice message into text\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **Azure AI Speech speech-to-text (Microsoft Corporation)**: Fast transcription returns the text synchronously for short files; real-time recognize-once is the SDK path. No silence fixture was run.\n- **Deepgram Speech-to-Text (Nova-3, Flux) (Deepgram, Inc.)**: Pre-recorded is synchronous over HTTP and returns the transcript in the response; Pipecat puts Nova-3 finals at 247 ms. No silence fixture was run.\n- **Inworld STT (Theai, Inc. dba Inworld AI)**: Synchronous POST transcribe returns the transcript for requests to 16 MiB; no silence fixture was run.\n- **MiniMax Speech-to-Text (Nanonoble Pte. Ltd.)**: Synchronous transcription of clips to 500 seconds with a language header; the guide claims tuning against hallucination, which is a vendor claim.\n- **Mistral Voxtral Transcribe (Mistral AI (RCS Paris 952 418 325))**: Synchronous /v1/audio/transcriptions returns the text; acc-09 reports no hallucination on silence for daily use.\n- **Nemotron 3.5 ASR Streaming 0.6B (NVIDIA Corporation)**: A 0.6B model running faster than real time on a small GPU or laptop via Transformers pipeline or NeMo-Speech.cpp; silence behaviour is undocumented.\n- **OpenAI Speech to Text (OpenAI OpCo, LLC)**: Synchronous /v1/audio/transcriptions with gpt-transcribe returns the text; no silence fixture was run and acc-15 used an LLM pass to fix Whisper hallucinations.\n- **Parakeet TDT 0.6B v3 (NVIDIA Corporation)**: acc-17 reports near-instant local dictation on a MacBook; Transformers 5.10 pipeline runs it. Silence behaviour undocumented.\n- **Smallest.ai Pulse STT (Smallest, Inc.)**: POST /waves/v1/stt/ is synchronous without webhook_url and returns the transcript; silence behaviour untested.\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- **Amazon Transcribe (Amazon Web Services, Inc.)**: Batch jobs are asynchronous with S3 input and polling, so a 30-second clip is not back within 2 seconds; streaming works but the median final latency is 1,136 ms.\n- **AssemblyAI Speech-to-Text (Universal) (AssemblyAI, Inc.)**: Pre-recorded is an asynchronous job with polling and a 403 rate limit; the streaming path returns finals in about 300 ms but needs a WebSocket. Silence behaviour untested.\n- **Cartesia Ink (Cartesia AI, Inc.)**: Batch ink-whisper returns a transcript synchronously; realtime finals arrive in about 300 ms. Silence behaviour untested, and realtime bills silence.\n- **Cohere Transcribe 03-2026 (Cohere Inc.)**: A 2B model transcribes a clip quickly on a GPU, but the blog says it is eager to transcribe non-speech sounds, so a partly silent clip needs a VAD in front.\n- **ElevenLabs Scribe Speech to Text API (Eleven Labs Inc.)**: POST /v1/speech-to-text is synchronous and takes clips from 100 ms, but a request under one credit bills one credit and no silence fixture was run.\n- **Giggy Speech to Text (Giggy)**: Recordings from 0.5 seconds are accepted, but every recorded request is an HTTP 202 then polling, and input must be converted to 16 kHz mono WAV first.\n- **Gladia Speech-to-Text API + MCP (Gladia SAS)**: Pre-recorded is an asynchronous job (init, upload, poll or callback), so a 30-second clip is not back within 2 seconds; live sessions suit it better.\n- **Google Cloud Speech-to-Text (Google LLC)**: Synchronous Recognize takes up to 1 minute or 10 MB and returns directly, but acc-05 saw repeated filler text on noisy or silent audio and a 403 on 20 seconds of silence.\n- **Groq Speech-to-Text (Groq LLC)**: Synchronous transcription of a short file is fast on Groq, but every request bills at least 10 seconds and verbose_json exposes no_speech_prob rather than suppressing silence.\n- **IBM Watson Speech to Text (International Business Machines Corporation)**: Synchronous /v1/recognize returns text for a short clip, but the 30-second inactivity timeout and no silence fixture leave the silence case unchecked.\n- **Ming-3.0-asr-tiny (inclusionAI, Ant Group (named in the site footer of inclusion-ai.org; the LICENSE copyright line reads inclusionAI))**: A short clip transcribes in one pass on a CUDA GPU, but the model needs 17.7 GB of BF16 weights and no silence behaviour is documented.\n- **Ming-3.0-audio-tiny (inclusionAI (Ant Group))**: A clip transcribes on one GPU with about 25 GB free, but loading runs repository code and silence behaviour is undocumented.\n- **Qwen3-ASR-0.6B (Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check))**: Fast on a small GPU through vLLM, but acc-25 reports noise returned as filler interjections and heavy repetition on non-speech sound.\n- **Qwen3-ASR-1.7B (Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check))**: Fast on a small GPU through vLLM, but acc-25 reports noise returned as filler interjections and heavy repetition on non-speech sound.\n- **Rev AI Speech-to-Text API (Rev.com, Inc.)**: Async jobs poll or call back, so a 30-second clip is not back within 2 seconds, and every job bills at least 15 seconds.\n- **Soniox Speech-to-Text (Soniox Inc.)**: The async API is a job with upload and polling; the realtime socket returns finals in about 266 ms but needs a stream. Silence behaviour untested.\n- **Speechmatics Speech-to-Text (Cantab Research Ltd)**: Batch is a job with polling (5-second default wait) or notifications, so a clip is not back within 2 seconds; realtime finals arrive in 369 to 495 ms.\n- **Underdog Bark 3.0 (Conway Research)**: About 1.5 seconds per minute of audio on an M2 per the card, but every route runs Conway's Python and the first run needs the network and about 6 GB to extract.\n- **Voxtral Mini 4B Realtime 2602 (Mistral AI (RCS Paris 952 418 325))**: Runs on a 16 GB GPU in vLLM or as a Q4 GGUF in llama.cpp, but output is plain text and silence behaviour is undocumented.\n\n- not this job: Ming-3.0-audio-flash (inclusionAI, Ant Group (named in the inclusion-ai.org footer; no registered company named)): Needs a multi-GPU server (259 GB BF16), so not a path for a waiting user on a laptop or one GPU.\n\n3 listings in the category were added after this reading and aren't marked yet.\n\n## What stops agents finishing\n\n- every request billed as at least 10 seconds (Groq), so many short clips cost more than their length\n- tool must have 16 kHz mono WAV and nothing else (Giggy)\n- noise or breath transcribed as filler words (acc-25)\n\n## Around it\n\nBefore: voice.capture-microphone. After: llm.prompt, editor.insert-text.\n\n## Where this comes from\n\nWeight 10 of 100 in Speech-to-text: 4 of 32 accounts (acc-05, acc-17, acc-18, acc-25); heavily represented in Hacker News dictation-app threads, where local models dominate\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/speech-to-text.dictation-to-agent.json, or the MCP tool get_use_case with id speech-to-text.dictation-to-agent. 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": "Dictate a short clip into text for an agent or editor",
        "url": ""
      }
    ],
    "description": "Dictate a short clip into text for an agent or editor: 8 companies fully do it, 17 with a limit, 42 carry the tag. Every listing in Speech-to-text with the reason and a source.",
    "facts": null,
    "h1": "Dictate a short clip into text for an agent or editor",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/speech-to-text.dictation-to-agent/",
    "published": "",
    "section": "agents",
    "title": "Dictate a short clip into text for an agent or editor | Anchor…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/speech-to-text.dictation-to-agent/"
  },
  "tokens": {
    "markdown": 2100,
    "slim": 580
  },
  "version": 1
}
