{
  "listings": [
    {
      "slug": "amazon-transcribe",
      "name": "Amazon Transcribe",
      "company": "Amazon Web Services, Inc.",
      "grade": "BB",
      "fit": "yes",
      "why": "ShowSpeakerLabels with MaxSpeakerLabels 2 to 30 on batch jobs; files to 28,800 seconds and 2 GB, so a 3-hour meeting runs as one job without chunking.",
      "source": "https://docs.aws.amazon.com/transcribe/latest/APIReference/API_Settings.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": "yes",
      "why": "speaker_labels with speakers_expected or min and max caps on files to 10 hours and 5 GB in one job; labels are generic A, B (acc-03) and acc-30 lost text on the legacy tier.",
      "source": "https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/assemblyai-stt"
    },
    {
      "slug": "azure-speech-to-text",
      "name": "Azure AI Speech speech-to-text",
      "company": "Microsoft Corporation",
      "grade": "BB",
      "fit": "yes",
      "why": "Fast transcription takes diarization maxSpeakers 2 to 35 on files under 5 hours and 500 MB; batch transcription has diarizationEnabled and 1 GB files.",
      "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": "elevenlabs-scribe",
      "name": "ElevenLabs Scribe Speech to Text API",
      "company": "Eleven Labs Inc.",
      "grade": "BB",
      "fit": "yes",
      "why": "diarize with num_speakers up to 32 on files to 5 GB and 15 hours in one request; use_speaker_library matches registered speakers across jobs.",
      "source": "https://elevenlabs.io/docs/api-reference/speech-to-text/convert",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/elevenlabs-scribe"
    },
    {
      "slug": "rev-ai-stt",
      "name": "Rev AI Speech-to-Text API",
      "company": "Rev.com, Inc.",
      "grade": "C",
      "fit": "yes",
      "why": "Diarisation is on unless skip_diarization is set, on media to 17 hours and 2 GB in one job; no speaker cap is documented.",
      "source": "https://docs.rev.ai/_bundle/api/asynchronous/reference.yaml",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/rev-ai-stt"
    },
    {
      "slug": "speechmatics-stt",
      "name": "Speechmatics Speech-to-Text",
      "company": "Cantab Research Ltd",
      "grade": "BB",
      "fit": "yes",
      "why": "diarization speaker with speaker_diarization_config.max_speakers (unrestricted if omitted) and sensitivity; batch files to 1 GB inline or larger via fetch_data URL. acc-01 ranked it last on postcodes, not speakers.",
      "source": "https://docs.speechmatics.com/speech-to-text/batch/batch-diarization",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/speechmatics-stt"
    },
    {
      "slug": "deepgram-stt",
      "name": "Deepgram Speech-to-Text (Nova-3, Flux)",
      "company": "Deepgram, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "diarize_model v2 labels every word on files to 2 GB in one request, but no speaker cap is documented and acc-29 saw accuracy drop past four speakers.",
      "source": "https://developers.deepgram.com/docs/diarization",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/deepgram-stt"
    },
    {
      "slug": "gladia-stt",
      "name": "Gladia Speech-to-Text API + MCP",
      "company": "Gladia SAS",
      "grade": "BB",
      "fit": "caveat",
      "why": "diarization with number_of_speakers, min and max hints (not enforced) on pre-recorded files to 135 minutes and 1,000 MB; a 3-hour meeting must be split, which restarts speaker labels.",
      "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": "diarization_config with min and max speaker counts; Chirp 3 diarises only in BatchRecognize from Cloud Storage, files to 8 hours. acc-11 says live diarisation stops at about three speakers.",
      "source": "https://docs.cloud.google.com/speech-to-text/docs/models/chirp-3",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/google-speech-to-text"
    },
    {
      "slug": "ibm-watson-stt",
      "name": "IBM Watson Speech to Text",
      "company": "International Business Machines Corporation",
      "grade": "C",
      "fit": "caveat",
      "why": "speaker_labels works on HTTP and WebSocket requests to 1 GB async, but is optimised for two speakers with a six-speaker maximum and undefined behaviour beyond.",
      "source": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-speaker-labels",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/ibm-watson-stt"
    },
    {
      "slug": "inworld-stt",
      "name": "Inworld STT",
      "company": "Theai, Inc. dba Inworld AI",
      "grade": "C",
      "fit": "caveat",
      "why": "enableSpeakerDiarization is experimental, applies to the streaming endpoint, and labels per stream; async jobs to 512 MB say diarisation works as synchronously, with no speaker cap.",
      "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": "caveat",
      "why": "verbose_json returns n_speakers and speaker on each segment, but requests stop at 500 seconds, so any meeting must be split and speaker labels restart per chunk.",
      "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": "caveat",
      "why": "diarize with timestamp_granularities segment gives speaker_id per segment on batch; the 3-hour limit is a vendor claim and the card says one speaker is kept on overlap. acc-09 found it good for podcasts.",
      "source": "https://docs.mistral.ai/studio/audio/speech_to_text/offline_transcription",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mistral-voxtral-transcribe"
    },
    {
      "slug": "openai-speech-to-text",
      "name": "OpenAI Speech to Text",
      "company": "OpenAI OpCo, LLC",
      "grade": "BB",
      "fit": "caveat",
      "why": "Only the deprecated gpt-4o-transcribe-diarize returns diarized_json, within 25 MB per file, so long meetings are chunked and labels flip per chunk (acc-20); it shuts on 2027-02-26.",
      "source": "https://developers.openai.com/api/docs/guides/speech-to-text",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/openai-speech-to-text"
    },
    {
      "slug": "smallest-pulse-stt",
      "name": "Smallest.ai Pulse STT",
      "company": "Smallest, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "diarize adds per-word and per-utterance speaker labels on pre-recorded files, but no speaker cap is stated and Pulse Pro caps audio at 250 MB.",
      "source": "https://docs.smallest.ai/openapi/models-api.json",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/smallest-pulse-stt"
    },
    {
      "slug": "soniox-stt",
      "name": "Soniox Speech-to-Text",
      "company": "Soniox Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "enable_speaker_diarization labels every token on async files to 300 minutes, so a 3-hour file is split; no speaker cap is stated. acc-11 says Soniox does live speakers well.",
      "source": "https://docs.soniox.com/stt/concepts/speaker-diarization",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/soniox-stt"
    },
    {
      "slug": "cartesia-ink-stt",
      "name": "Cartesia Ink",
      "company": "Cartesia AI, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "No diarisation parameter on either endpoint; batch POST /stt accepts ink-whisper only.",
      "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": "no",
      "why": "The docs state the model has neither timestamps nor speaker diarisation.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cohere-transcribe-03-2026"
    },
    {
      "slug": "giggy-stt",
      "name": "Giggy Speech to Text",
      "company": "Giggy",
      "grade": "E",
      "fit": "no",
      "why": "No speaker labels; the docs list speaker labels among the functions the API does not return.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/giggy-stt"
    },
    {
      "slug": "groq-speech-to-text",
      "name": "Groq Speech-to-Text",
      "company": "Groq LLC",
      "grade": "BB",
      "fit": "no",
      "why": "No diarisation parameter on the OpenAI-compatible endpoints.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/groq-speech-to-text"
    },
    {
      "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": "no",
      "why": "Card states output has no speaker diarisation.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/ming-3-0-asr-tiny"
    },
    {
      "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": "No diarisation or speaker output on the card.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/ming-3-0-audio-flash"
    },
    {
      "slug": "ming-3-0-audio-tiny",
      "name": "Ming-3.0-audio-tiny",
      "company": "inclusionAI (Ant Group)",
      "grade": "D",
      "fit": "no",
      "why": "No diarisation on the card.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/ming-3-0-audio-tiny"
    },
    {
      "slug": "nemotron-3-5-asr-streaming-0-6b",
      "name": "Nemotron 3.5 ASR Streaming 0.6B",
      "company": "NVIDIA Corporation",
      "grade": "C",
      "fit": "no",
      "why": "No diarisation; plain text out.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/nemotron-3-5-asr-streaming-0-6b"
    },
    {
      "slug": "parakeet-tdt-0-6b-v3",
      "name": "Parakeet TDT 0.6B v3",
      "company": "NVIDIA Corporation",
      "grade": "B",
      "fit": "no",
      "why": "No diarisation; acc-12 paired it with a separate diarisation model.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3"
    },
    {
      "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": "no",
      "why": "No diarisation; acc-08 chained pyannote separately.",
      "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": "no",
      "why": "No diarisation; acc-08 chained pyannote separately.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/qwen3-asr-1-7b"
    },
    {
      "slug": "underdog-bark-3",
      "name": "Underdog Bark 3.0",
      "company": "Conway Research",
      "grade": "E",
      "fit": "no",
      "why": "Plain text only, no speaker labels.",
      "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": "no",
      "why": "No diarisation or segments for the weights.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602"
    }
  ],
  "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": 9,
    "after": [
      "llm.summarise",
      "document-extraction.action-items",
      "notes.store"
    ],
    "area": "voice",
    "asks": [
      "transcribe this meeting and label the speakers",
      "who said what in this call",
      "give me notes with each action item attributed"
    ],
    "before": [
      "meetings.record",
      "storage.fetch-file"
    ],
    "blockers": [
      "diarisation restarts per chunk when the file must be split (OpenAI 25 MB cap, acc-20)",
      "no diarisation at all (Groq, Giggy, Cohere Transcribe, Parakeet, Nemotron, Voxtral Realtime weights)",
      "speaker labels returned as A, B, C with no way to name them without a human step",
      "accuracy collapses past 4 speakers (acc-29)"
    ],
    "capabilities": [
      "speech.stt",
      "speech.batch",
      "speech.diarisation"
    ],
    "category": "speech-to-text",
    "categoryName": "Speech-to-text",
    "checked": "2026-11-12",
    "companies": {
      "fit": 6,
      "fitWithLimit": 10,
      "tagged": 45
    },
    "competition": "crowded",
    "fits": [
      "amazon-transcribe",
      "assemblyai-stt",
      "azure-speech-to-text",
      "elevenlabs-scribe",
      "rev-ai-stt",
      "speechmatics-stt"
    ],
    "fitsWithLimit": [
      "deepgram-stt",
      "gladia-stt",
      "google-speech-to-text",
      "ibm-watson-stt",
      "inworld-stt",
      "minimax-stt",
      "mistral-voxtral-transcribe",
      "openai-speech-to-text",
      "smallest-pulse-stt",
      "soniox-stt"
    ],
    "id": "speech-to-text.meeting-with-speakers",
    "listings": {
      "caveat": 10,
      "no": 13,
      "notRead": 3,
      "tagged": 55,
      "unchecked": 0,
      "yes": 6
    },
    "name": "Transcribe a recorded meeting or call and say who said what",
    "status": "draft",
    "success": "A transcript with a stable speaker label on every segment, labels consistent across the whole file including any chunks, in one job. Measured: speaker count within one of the true count.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/speech-to-text.meeting-with-speakers.json",
    "weight": 20,
    "weightBasis": "10 of 32 accounts (acc-03, acc-06, acc-10, acc-11, acc-13, acc-20, acc-26, acc-29, acc-32, acc-09); the most common failure reported was attribution, not words"
  }
}
