{
  "listings": [
    {
      "slug": "azure-speech-to-text",
      "name": "Azure AI Speech speech-to-text",
      "company": "Microsoft Corporation",
      "grade": "BB",
      "fit": "yes",
      "why": "Fast transcription returns the text synchronously for short files; real-time recognize-once is the SDK path. No silence fixture was run.",
      "source": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/azure-speech-to-text"
    },
    {
      "slug": "deepgram-stt",
      "name": "Deepgram Speech-to-Text (Nova-3, Flux)",
      "company": "Deepgram, Inc.",
      "grade": "BB",
      "fit": "yes",
      "why": "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.",
      "source": "https://developers.deepgram.com/docs/pre-recorded-audio",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/deepgram-stt"
    },
    {
      "slug": "inworld-stt",
      "name": "Inworld STT",
      "company": "Theai, Inc. dba Inworld AI",
      "grade": "C",
      "fit": "yes",
      "why": "Synchronous POST transcribe returns the transcript for requests to 16 MiB; no silence fixture was run.",
      "source": "https://docs.inworld.ai/api-reference/sttAPI/speechtotext/transcribe",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/inworld-stt"
    },
    {
      "slug": "minimax-stt",
      "name": "MiniMax Speech-to-Text",
      "company": "Nanonoble Pte. Ltd.",
      "grade": "D",
      "fit": "yes",
      "why": "Synchronous transcription of clips to 500 seconds with a language header; the guide claims tuning against hallucination, which is a vendor claim.",
      "source": "https://platform.minimax.io/docs/api-reference/speech-to-text",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/minimax-stt"
    },
    {
      "slug": "mistral-voxtral-transcribe",
      "name": "Mistral Voxtral Transcribe",
      "company": "Mistral AI (RCS Paris 952 418 325)",
      "grade": "B",
      "fit": "yes",
      "why": "Synchronous /v1/audio/transcriptions returns the text; acc-09 reports no hallucination on silence for daily use.",
      "source": "https://docs.mistral.ai/studio/audio/speech_to_text/offline_transcription",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mistral-voxtral-transcribe"
    },
    {
      "slug": "nemotron-3-5-asr-streaming-0-6b",
      "name": "Nemotron 3.5 ASR Streaming 0.6B",
      "company": "NVIDIA Corporation",
      "grade": "C",
      "fit": "yes",
      "why": "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.",
      "source": "https://github.com/huggingface/transformers/blob/main/docs/source/en/model_doc/nemotron3_5_asr.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/nemotron-3-5-asr-streaming-0-6b"
    },
    {
      "slug": "openai-speech-to-text",
      "name": "OpenAI Speech to Text",
      "company": "OpenAI OpCo, LLC",
      "grade": "BB",
      "fit": "yes",
      "why": "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.",
      "source": "https://developers.openai.com/api/docs/guides/speech-to-text",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/openai-speech-to-text"
    },
    {
      "slug": "parakeet-tdt-0-6b-v3",
      "name": "Parakeet TDT 0.6B v3",
      "company": "NVIDIA Corporation",
      "grade": "B",
      "fit": "yes",
      "why": "acc-17 reports near-instant local dictation on a MacBook; Transformers 5.10 pipeline runs it. Silence behaviour undocumented.",
      "source": "https://news.ycombinator.com/item?id=46497820",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3"
    },
    {
      "slug": "smallest-pulse-stt",
      "name": "Smallest.ai Pulse STT",
      "company": "Smallest, Inc.",
      "grade": "B",
      "fit": "yes",
      "why": "POST /waves/v1/stt/ is synchronous without webhook_url and returns the transcript; silence behaviour untested.",
      "source": "https://docs.smallest.ai/openapi/models-api.json",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/smallest-pulse-stt"
    },
    {
      "slug": "amazon-transcribe",
      "name": "Amazon Transcribe",
      "company": "Amazon Web Services, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.aws.amazon.com/general/latest/gr/transcribe.html",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/amazon-transcribe"
    },
    {
      "slug": "assemblyai-stt",
      "name": "AssemblyAI Speech-to-Text (Universal)",
      "company": "AssemblyAI, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://www.assemblyai.com/docs/streaming/message-sequence",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/assemblyai-stt"
    },
    {
      "slug": "cartesia-ink-stt",
      "name": "Cartesia Ink",
      "company": "Cartesia AI, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Batch ink-whisper returns a transcript synchronously; realtime finals arrive in about 300 ms. Silence behaviour untested, and realtime bills silence.",
      "source": "https://docs.cartesia.ai/api-reference/stt/transcribe",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cartesia-ink-stt"
    },
    {
      "slug": "cohere-transcribe-03-2026",
      "name": "Cohere Transcribe 03-2026",
      "company": "Cohere Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "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.",
      "source": "https://huggingface.co/blog/CohereLabs/cohere-transcribe-03-2026-release",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cohere-transcribe-03-2026"
    },
    {
      "slug": "elevenlabs-scribe",
      "name": "ElevenLabs Scribe Speech to Text API",
      "company": "Eleven Labs Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://elevenlabs.io/docs/api-reference/speech-to-text/convert",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/elevenlabs-scribe"
    },
    {
      "slug": "giggy-stt",
      "name": "Giggy Speech to Text",
      "company": "Giggy",
      "grade": "E",
      "fit": "caveat",
      "why": "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.",
      "source": "https://giggy.ai/docs/speech-api",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/giggy-stt"
    },
    {
      "slug": "gladia-stt",
      "name": "Gladia Speech-to-Text API + MCP",
      "company": "Gladia SAS",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.gladia.io/api-reference/v2/pre-recorded/init",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/gladia-stt"
    },
    {
      "slug": "google-speech-to-text",
      "name": "Google Cloud Speech-to-Text",
      "company": "Google LLC",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.cloud.google.com/speech-to-text/docs/quotas",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/google-speech-to-text"
    },
    {
      "slug": "groq-speech-to-text",
      "name": "Groq Speech-to-Text",
      "company": "Groq LLC",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://console.groq.com/docs/speech-to-text",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/groq-speech-to-text"
    },
    {
      "slug": "ibm-watson-stt",
      "name": "IBM Watson Speech to Text",
      "company": "International Business Machines Corporation",
      "grade": "C",
      "fit": "caveat",
      "why": "Synchronous /v1/recognize returns text for a short clip, but the 30-second inactivity timeout and no silence fixture leave the silence case unchecked.",
      "source": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-websockets",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/ibm-watson-stt"
    },
    {
      "slug": "ming-3-0-asr-tiny",
      "name": "Ming-3.0-asr-tiny",
      "company": "inclusionAI, Ant Group (named in the site footer of inclusion-ai.org; the LICENSE copyright line reads inclusionAI)",
      "grade": "C",
      "fit": "caveat",
      "why": "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.",
      "source": "https://huggingface.co/inclusionAI/Ming-3.0-asr-tiny",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/ming-3-0-asr-tiny"
    },
    {
      "slug": "ming-3-0-audio-tiny",
      "name": "Ming-3.0-audio-tiny",
      "company": "inclusionAI (Ant Group)",
      "grade": "D",
      "fit": "caveat",
      "why": "A clip transcribes on one GPU with about 25 GB free, but loading runs repository code and silence behaviour is undocumented.",
      "source": "https://huggingface.co/inclusionAI/Ming-3.0-audio-tiny",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/ming-3-0-audio-tiny"
    },
    {
      "slug": "qwen3-asr-0-6b",
      "name": "Qwen3-ASR-0.6B",
      "company": "Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check)",
      "grade": "C",
      "fit": "caveat",
      "why": "Fast on a small GPU through vLLM, but acc-25 reports noise returned as filler interjections and heavy repetition on non-speech sound.",
      "source": "https://huggingface.co/Qwen/Qwen3-ASR-0.6B",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/qwen3-asr-0-6b"
    },
    {
      "slug": "qwen3-asr-1-7b",
      "name": "Qwen3-ASR-1.7B",
      "company": "Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check)",
      "grade": "B",
      "fit": "caveat",
      "why": "Fast on a small GPU through vLLM, but acc-25 reports noise returned as filler interjections and heavy repetition on non-speech sound.",
      "source": "https://huggingface.co/Qwen/Qwen3-ASR-1.7B",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/qwen3-asr-1-7b"
    },
    {
      "slug": "rev-ai-stt",
      "name": "Rev AI Speech-to-Text API",
      "company": "Rev.com, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.rev.ai/_bundle/api/asynchronous/reference.yaml",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/rev-ai-stt"
    },
    {
      "slug": "soniox-stt",
      "name": "Soniox Speech-to-Text",
      "company": "Soniox Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.soniox.com/stt/api-reference/websocket-api",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/soniox-stt"
    },
    {
      "slug": "speechmatics-stt",
      "name": "Speechmatics Speech-to-Text",
      "company": "Cantab Research Ltd",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.speechmatics.com/speech-to-text/batch/limits",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/speechmatics-stt"
    },
    {
      "slug": "underdog-bark-3",
      "name": "Underdog Bark 3.0",
      "company": "Conway Research",
      "grade": "E",
      "fit": "caveat",
      "why": "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.",
      "source": "https://huggingface.co/ConwayResearch/Underdog-Bark-3.0",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/underdog-bark-3"
    },
    {
      "slug": "voxtral-mini-4b-realtime-2602",
      "name": "Voxtral Mini 4B Realtime 2602",
      "company": "Mistral AI (RCS Paris 952 418 325)",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602"
    },
    {
      "slug": "ming-3-0-audio-flash",
      "name": "Ming-3.0-audio-flash",
      "company": "inclusionAI, Ant Group (named in the inclusion-ai.org footer; no registered company named)",
      "grade": "E",
      "fit": "no",
      "why": "Needs a multi-GPU server (259 GB BF16), so not a path for a waiting user on a laptop or one GPU.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/ming-3-0-audio-flash"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "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"
  },
  "useCase": {
    "accounts": 4,
    "after": [
      "llm.prompt",
      "editor.insert-text"
    ],
    "area": "voice",
    "asks": [
      "transcribe this 20-second voice note",
      "I'll speak my prompt, type it for me",
      "turn this voice message into text"
    ],
    "before": [
      "voice.capture-microphone"
    ],
    "blockers": [
      "every request billed as at least 10 seconds (Groq), so many short clips cost more than their length",
      "tool must have 16 kHz mono WAV and nothing else (Giggy)",
      "noise or breath transcribed as filler words (acc-25)"
    ],
    "capabilities": [
      "speech.stt",
      "speech.batch"
    ],
    "category": "speech-to-text",
    "categoryName": "Speech-to-text",
    "checked": "2026-11-12",
    "companies": {
      "fit": 8,
      "fitWithLimit": 17,
      "tagged": 42
    },
    "competition": "crowded",
    "fits": [
      "azure-speech-to-text",
      "deepgram-stt",
      "inworld-stt",
      "minimax-stt",
      "mistral-voxtral-transcribe",
      "nemotron-3-5-asr-streaming-0-6b",
      "openai-speech-to-text",
      "parakeet-tdt-0-6b-v3",
      "smallest-pulse-stt"
    ],
    "fitsWithLimit": [
      "amazon-transcribe",
      "assemblyai-stt",
      "cartesia-ink-stt",
      "cohere-transcribe-03-2026",
      "elevenlabs-scribe",
      "giggy-stt",
      "gladia-stt",
      "google-speech-to-text",
      "groq-speech-to-text",
      "ibm-watson-stt",
      "ming-3-0-asr-tiny",
      "ming-3-0-audio-tiny",
      "qwen3-asr-0-6b",
      "qwen3-asr-1-7b",
      "rev-ai-stt",
      "soniox-stt",
      "speechmatics-stt",
      "underdog-bark-3",
      "voxtral-mini-4b-realtime-2602"
    ],
    "id": "speech-to-text.dictation-to-agent",
    "listings": {
      "caveat": 19,
      "no": 1,
      "notRead": 3,
      "tagged": 52,
      "unchecked": 0,
      "yes": 9
    },
    "name": "Dictate a short clip into text for an agent or editor",
    "status": "draft",
    "success": "Clean punctuated text back for a 30-second clip. Measured: the text arrives within 2 seconds of the clip ending, with no filler text or hallucinated sentence on a clip that is partly silent.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/speech-to-text.dictation-to-agent.json",
    "weight": 10,
    "weightBasis": "4 of 32 accounts (acc-05, acc-17, acc-18, acc-25); heavily represented in Hacker News dictation-app threads, where local models dominate"
  }
}
