For AI agents: every API docs page in one plain-text file is at /docs/llms-full.txt, and the documentation index is at /llms.txt. This page is available as Markdown at https://diffio.ai/docs/api-reference/get-transcript.md, and every docs URL returns Markdown when requested with Accept: text/markdown.

Get a generation's transcript
Returns a generation's word-timed transcript in a normalized TranscriptWord shape, ready to display or pass back to Edit a generation's transcript and Ask the edit assistant.
GET https:/
- Key scope:
generations:read - Auth header:
Authorization: Bearer <apiKey> - Body: None
Request
Pass project_id and generation_id in the path, and optional preview_seconds in the query string.
Path parameters
Query parameters
| Field | Type | Required | Description |
|---|---|---|---|
#preview_seconds | integer | Required: No | Optional limit in seconds, from 4 to 3600 (rounded up to whole 4-second segments). Keeps only words starting within the preview. |
Headers
| Field | Type | Required | Description |
|---|---|---|---|
#Diffio-End-User | string | Required: No | Optional end-user identifier (up to 128 characters). Scopes the request to that end user's projects; omit to act across the whole account. |
Request
import os
from diffio import DiffioClient
key = os.environ["DIFFIO_API_KEY"]
client = DiffioClient(api_key=key)
transcript = client.transcripts.get(
"62f62565-049f-5e7e-bbd2-9de0cf7ddbfe",
"ce832a32-a1ce-516a-b8bd-75457bd8517f",
)Response
Returns the normalized transcript with full text and ordered words.
Success: 200OK.
Response fields
| Field | Type | Present | Description |
|---|---|---|---|
#object | string | Always | Resource type, always "transcript".transcript |
#generation_id | string | Always | Identifier of the generation. |
#text | string | Always | Full transcript text (or the preview's words joined by spaces when preview_seconds is set). |
#words | array | Always | Ordered array of word-timed TranscriptWord objects.Fields below |
#truncated | boolean | Always | True when words starting at or after preview_seconds were omitted. |
words[] 7 fields
| Field | Type | Present | Description |
|---|---|---|---|
#words[] | string | Always | Stable word identifier within the transcript (stored ID or word-{index}). |
#words[] | string | Always | Transcribed word text. |
#words[] | number | null | Always | Word start timestamp in seconds on the recording, or null when untimed. |
#words[] | number | null | Always | Word end timestamp in seconds on the recording, or null when untimed. |
#words[] | number | null | Always | Transcriber confidence from 0 to 1, or null when unknown. |
#words[] | string | Sometimes | Speaker label when recorded by the transcriber (omitted on preview_seconds reads). |
#words[] | string | Sometimes | Word language code when recorded by the transcriber. |
Response 200OK.
{
"object": "transcript",
"generation_id": "ce832a32-a1ce-516a-b8bd-75457bd8517f",
"text": "For the lives of women have been more affected by its new horizons than those of any other group. Profound and stirring as have been accomplishments in the remoter fields of pure research, it is in the home that the applications of scientific achievement have perhaps been most far-reaching, and it is through changing conditions there that women have become the greatest beneficiaries in the modern scheme. Science has released them from much",
"words": [
{
"id": "word-0",
"text": "For",
"start": 0.6,
"end": 0.8,
"probability": null,
"language": "en",
"label": "speech"
},
{
"id": "word-1",
"text": "the",
"start": 0.84,
"end": 0.94,
"probability": null,
"language": "en",
"label": "speech"
},
{
"id": "word-2",
"text": "lives",
"start": 1.04,
"end": 1.32,
"probability": null,
"language": "en",
"label": "speech"
}
],
"truncated": false
}Return codes
200OK.Returns the normalized word-timed transcript.400Bad request.preview_secondsis outside4to3600, orDiffio-End-Userexceeds 128 characters.invalid_parameterinvalid_header403Forbidden: the key lacks permission.Key is inactive or lacksgenerations:read.permission_denied404Not found.Project not found, or 2 more causes
- Project not found
- Generation not found
- Finished generation has no stored transcript
project_not_foundgeneration_not_foundtranscript_not_found409Conflict: see error.code for which one.transcription_statusis stillpreparingor the generation is running, or transcription failed;details.transcription_statusreports the state.not_readynot_available422Unprocessable request.Stored transcript file could not be parsed.transcript_unreadable401Unauthorized: the API key is missing or invalid.405Client error.Same on every endpoint401Unauthorized: the API key is missing or invalid. Missing API key (code missing_api_key), or invalid API key (code invalid_api_key).405Client error. HTTP method not supported on this path; check the Allow header (code method_not_allowed).
Example error response
Errors are JSON: an error object with code, message and request_id. An unrecognized key returns 401Unauthorized: the API key is missing or invalid.:
{
"error": {
"code": "invalid_api_key",
"message": "Invalid API key.",
"request_id": "dead773b60e148fd9e22d680a22fa701"
}
}Notes
- Both Flash and Pro restores produce a word-timed transcript (
transcription_status: "ready"), while only Pro restores support Edit a generation's transcript. - Pass the
wordsarray directly toPOST .../edits,POST .../edits/estimate, orPOST .../transcript/assistant/turnswith your word-level edits applied.