Skip to content
HALOWERK

Tonwerk

verbatim protocol

Speakers come from audio channels: with a two-channel recording (e.g. a call or an interview with one microphone per person) each channel is one speaker; identical channels or a mono file give one speaker (no voice-based diarisation). Per channel Silero VAD v6.2 finds the speech and OpenAI Whisper base (MIT; ONNX export Xenova/whisper-base, pinned) transcribes it with timestamps; line times are snapped to the detected speech. A line is unclear when the mean token log-probability is below.

POST https://ton.halowerk.com/v1/verbatim-protocol

Inputs

Fields of the published input schema
FieldTypeRequiredDescription
audio_base64stringNoConversation recording; with two channels each channel is one speaker, at most 30 s, as base64 (max 10 MiB): WAV, FLAC, MP3, AAC/M4A, Ogg Vorbis/Opus, WebM and other common formats.
audio_urlstringNoInstead of base64: public http(s) URL of the file (max 10 MiB).
speaker_namesarrayNoNames for channel 1 and 2 (default Speaker 1, Speaker 2).
languagestringNoWhisper language code (ISO 639-1 such as en, de, fr; haw for Hawaiian). Omit to detect.
separate_channelsbooleanNoTreat the first two channels as separate speakers; false mixes them to one speaker.
unclear_logprobnumberNoLines with a lower mean token log-probability are marked unclear.
pause_min_snumberNoShortest silence of all speakers reported as a pause.
Show full input schema
{
  "type": "object",
  "additionalProperties": false,
  "properties": {
    "audio_base64": {
      "type": "string",
      "minLength": 16,
      "maxLength": 14000000,
      "description": "Conversation recording; with two channels each channel is one speaker, at most 30 s, as base64 (max 10 MiB): WAV, FLAC, MP3, AAC/M4A, Ogg Vorbis/Opus, WebM and other common formats."
    },
    "audio_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048,
      "description": "Instead of base64: public http(s) URL of the file (max 10 MiB)."
    },
    "speaker_names": {
      "type": "array",
      "maxItems": 2,
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 40,
        "pattern": "^[^\\x00-\\x1f]+$"
      },
      "description": "Names for channel 1 and 2 (default Speaker 1, Speaker 2)."
    },
    "language": {
      "type": "string",
      "pattern": "^[a-z]{2,3}$",
      "description": "Whisper language code (ISO 639-1 such as en, de, fr; haw for Hawaiian). Omit to detect."
    },
    "separate_channels": {
      "type": "boolean",
      "default": true,
      "description": "Treat the first two channels as separate speakers; false mixes them to one speaker."
    },
    "unclear_logprob": {
      "type": "number",
      "minimum": -3,
      "maximum": 0,
      "default": -1,
      "description": "Lines with a lower mean token log-probability are marked unclear."
    },
    "pause_min_s": {
      "type": "number",
      "minimum": 0.3,
      "maximum": 10,
      "default": 1,
      "description": "Shortest silence of all speakers reported as a pause."
    }
  }
}

Open original schema

Published input example

{
  "audio_base64": "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",
  "speaker_names": [
    "Host"
  ]
}

Result & documentation

Machine-readable documentation of this hub

Source of this page: the published HALOWERK catalog. Updated: 2026-11-17 UTC.

More endpoints in this hub

All endpoints in this hub โ†’