Transcripts

Working with Structured Transcript Data

The transcripts endpoint exposes machine-generated verbatim records of participant sessions in a structured JSON format. Each transcript object contains:

Speaker turns — identifies participant vs system/moderator.
Timestamps — millisecond-level markers for start and end of each segment.
Text content — normalized speech-to-text output.

Developers can:

Fetch the full transcript for a given responseId.
Use query parameters (e.g. start, end) to limit results to a time window.
Combine with video or audio metadata for playback sync.
Paginate long transcripts efficiently.

This endpoint is designed for downstream automation — powering search, summarization, highlight extraction, or integration into custom analysis pipelines — without requiring raw media processing.

Transcripts are available within each TestSessionRecording, which can be queried for via a TestResultNode.

Fetch a specific response transcript

Here we'll start our query at the the userTestResult resolver and from there select the recordings we're interested in, along with their transcripts.

# Start by selected a specific response using its UUID
query specificResult {
  userTestResult(
    resultUuid: "ut_response_9568e478-f8fe-450d-81e6-741a279c6b5b"
  ) {
    ...resultSelection
  }
}

# For the UserTestResult we need to fetch the appropriate recording...
fragment resultSelection on UserTestResult {
  name
  responseUUID
  status
  recordings {
    download {
      ...recordingSelection
    }
  }
  participant {
    anonymousId
    email
    name
  }
}

# On the TestSessionRecording we are mostly interested in the
# transcript but can also retrieve the video recording itself
fragment recordingSelection on TestSessionRecording {
  transcription
  videoUrl
  filesize
  duration
  startTime
  failedStatus
  failedType
  mimeType
  missingDataWarning
  isAudio
  usertestName
  createdAt
}

Fetch transcription for all responses to a specific test

Since we can fetch many responses for a single test, we're also able to fetch all transcripts at the same time.

(For info on pagination, see Pagination)

query listResults {
  userTest(uuid: "ut_645c4faa-5c2d-49b1-85fa-823ffbbbfa17") {
    id
    results(first: 4) {
      edges {
        node {
          ...resultSelection
        }
      }
    }
  }
}

Transcript data example

The transcript is returned as a JSON sting which will require decoding in your script itself.

It includes the entire transcript and also breaks the transcript down into individual sentences and words with individual timestamps.

Here's an example transcript, trimmed for brevity:

{
  "metadata": {
    "transaction_key": "deprecated",
    "created": "2025-09-10T10:38:08.750Z",
    "channels": 1,
    "models": ["1abfe86b-e047-4eed-858a-35e5625b41ee"],
    "request_id": "3df2e8a6-f1f2-4b19-82f9-4ba77a50311c",
    "model_info": {
      "1abfe86b-e047-4eed-858a-35e5625b41ee": {
        "arch": "nova-2",
        "name": "2-general-nova",
        "version": "2024-01-06.5664"
      }
    },
    "duration": 32.693687,
    "sha256": "196cac70fff22e8587b0f8a3f6249eb77f8ef4b0d19211da287be0461c604a81"
  },
  "results": {
    "channels": [
      {
        "detected_language": "en",
        "alternatives": [
          {
            "transcript": "Okay. This is a short transcript example. And if I wait a few seconds between sentences, it should break them out into different lines.",
            "paragraphs": {
              "transcript": "\\nSpeaker 0: Okay. This is a short transcript example. And if I wait a few seconds between sentences, it should break them out into different lines.",
              "paragraphs": [
                {
                  "end": 26.528687,
                  "speaker": 0,
                  "sentences": [
                    { "end": 9.5199995, "text": "Okay.", "start": 9.04 },
                    {
                      "end": 13.46,
                      "text": "This is a short transcript example.",
                      "start": 9.5199995
                    },
                    {
                      "end": 26.528687,
                      "text": "And if I wait a few seconds between sentences, it should break them out into different lines.",
                      "start": 16.055
                    }
                  ],
                  "start": 9.04,
                  "num_words": 24
                }
              ]
            },
            "words": [
              {
                "word": "okay",
                "start": 9.04,
                "speaker_confidence": 0.80801547,
                "confidence": 0.76546234,
                "speaker": 0,
                "end": 9.5199995,
                "punctuated_word": "Okay."
              },
              {
                "word": "this",
                "start": 9.5199995,
                "speaker_confidence": 0.80801547,
                "confidence": 0.999283,
                "speaker": 0,
                "end": 9.76,
                "punctuated_word": "This"
              }
            ],
            "confidence": 0.99968684
          }
        ],
        "language_confidence": 0.9562097
      }
    ],
    "utterances": [
      {
        "transcript": "Okay. This is a short transcript example.",
        "id": "1c11be29-5d2c-4591-ad4d-7716a7326a06",
        "start": 9.04,
        "confidence": 0.93274677,
        "speaker": 0,
        "end": 13.46,
        "words": [
          {
            "word": "okay",
            "start": 9.04,
            "speaker_confidence": 0.80801547,
            "confidence": 0.76546234,
            "speaker": 0,
            "end": 9.5199995,
            "punctuated_word": "Okay."
          },
          {
            "word": "this",
            "start": 9.5199995,
            "speaker_confidence": 0.80801547,
            "confidence": 0.999283,
            "speaker": 0,
            "end": 9.76,
            "punctuated_word": "This"
          },
          {
            "word": "is",
            "start": 9.76,
            "speaker_confidence": 0.80801547,
            "confidence": 0.99983037,
            "speaker": 0,
            "end": 10.24,
            "punctuated_word": "is"
          },
          {
            "word": "a",
            "start": 10.24,
            "speaker_confidence": 0.80801547,
            "confidence": 0.99959403,
            "speaker": 0,
            "end": 10.74,
            "punctuated_word": "a"
          },
          {
            "word": "short",
            "start": 11.12,
            "speaker_confidence": 0.80801547,
            "confidence": 0.99972695,
            "speaker": 0,
            "end": 11.62,
            "punctuated_word": "short"
          },
          {
            "word": "transcript",
            "start": 12,
            "speaker_confidence": 0.80801547,
            "confidence": 0.88348657,
            "speaker": 0,
            "end": 12.5,
            "punctuated_word": "transcript"
          },
          {
            "word": "example",
            "start": 12.96,
            "speaker_confidence": 0.80801547,
            "confidence": 0.88184386,
            "speaker": 0,
            "end": 13.46,
            "punctuated_word": "example."
          }
        ],
        "channel": 0
      }
    ]
  }
}