---
title: "Get sentences in transcript"
method: GET
path: "/v2/transcript/{transcript_id}/sentences"
tags: ["transcript"]
---

# Get sentences in transcript

`GET /v2/transcript/{transcript_id}/sentences`

<Note>To retrieve your transcriptions on our EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.</Note>
Get the transcript split by sentences. The API will attempt to semantically segment the transcript into sentences to create more reader-friendly transcripts.

## Path parameters

- `transcript_id` string, required

## Response `200`

Exported sentences

- SentencesResponse
  - `id` string, uuid, required — The unique identifier for the transcript
  - `confidence` number, double, required — The confidence score for the transcript
  - `audio_duration` number, required — The duration of the audio file in seconds
  - `sentences` TranscriptSentence[], required — An array of sentences in the transcript
    - `text` string, required — The transcript of the sentence
    - `start` integer, required — The starting time, in milliseconds, for the sentence
    - `end` integer, required — The ending time, in milliseconds, for the sentence
    - `confidence` number, double, required — The confidence score for the transcript of this sentence
    - `words` TranscriptWord[], required — An array of words in the sentence
      - `confidence` number, double, required — The confidence score for the transcript of this word
      - `start` integer, required — The starting time, in milliseconds, for the word
      - `end` integer, required — The ending time, in milliseconds, for the word
      - `text` string, required — The text of the word
      - `channel` string, nullable — The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.
      - `speaker` string, nullable, required — The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null
    - `channel` string, nullable — The channel of the sentence. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.
    - `speaker` string, nullable, required — The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null

## Other responses

- `400` — Bad request
- `401` — Unauthorized
- `404` — Not found
- `429` — Too many requests
- `500` — An error occurred while processing the request
- `503` — Service unavailable
- `504` — Gateway timeout

---

[API](https://skmtc.net/assemblyai/apis/assemblyai-api.md) · [All operations](https://skmtc.net/assemblyai/apis/assemblyai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/assemblyai/assemblyai-api/versions/f743e2ea9459/schema)