curl --request POST 'https://api.voicecheap.ai/v1/actions/transcripts_get' \
--header "x-api-key: $VOICECHEAP_API_KEY" \
--header 'Content-Type: application/json' \
--data '{"projectId":"project_launch_2026","source":"original","outputFormat":"json","includeSpeakerLabels":false}'
const input = {
projectId: 'project_launch_2026',
source: 'original',
outputFormat: 'json',
includeSpeakerLabels: false,
};
const response = await fetch('https://api.voicecheap.ai/v1/actions/transcripts_get', {
method: 'POST',
headers: {
'x-api-key': process.env.VOICECHEAP_API_KEY,
'Content-Type': 'application/json',
},
body: JSON.stringify(input),
});
const body = await response.json();
if (!response.ok) throw new Error(body.code + ': ' + body.message);
console.log(body);
import os
import requests
response = requests.post(
"https://api.voicecheap.ai/v1/actions/transcripts_get",
headers={"x-api-key": os.environ["VOICECHEAP_API_KEY"]},
json={"projectId": "project_launch_2026", "source": "original", "outputFormat": "json", "includeSpeakerLabels": False},
timeout=120,
)
body = response.json()
if not response.ok:
raise RuntimeError(f"{body.get('code')}: {body.get('message')}")
print(body)
{
"data": {
"format": "json",
"transcript": {
"source": "original",
"language": "fr",
"duration": 75,
"text": "Bienvenue au lancement.",
"speakers": [
{
"id": 0,
"label": "Speaker 1"
}
],
"segments": [
{
"index": 0,
"text": "Bienvenue au lancement.",
"begin": 0,
"end": 2,
"duration": 2,
"speaker": 0,
"language": "fr"
}
]
},
"contentType": "application/json"
}
}
Transcripts and editing
Get or export a project transcript
Retrieve the original or translated transcript as JSON, SRT or VTT, with optional speaker labels.
POST
/
v1
/
actions
/
transcripts_get
curl --request POST 'https://api.voicecheap.ai/v1/actions/transcripts_get' \
--header "x-api-key: $VOICECHEAP_API_KEY" \
--header 'Content-Type: application/json' \
--data '{"projectId":"project_launch_2026","source":"original","outputFormat":"json","includeSpeakerLabels":false}'
const input = {
projectId: 'project_launch_2026',
source: 'original',
outputFormat: 'json',
includeSpeakerLabels: false,
};
const response = await fetch('https://api.voicecheap.ai/v1/actions/transcripts_get', {
method: 'POST',
headers: {
'x-api-key': process.env.VOICECHEAP_API_KEY,
'Content-Type': 'application/json',
},
body: JSON.stringify(input),
});
const body = await response.json();
if (!response.ok) throw new Error(body.code + ': ' + body.message);
console.log(body);
import os
import requests
response = requests.post(
"https://api.voicecheap.ai/v1/actions/transcripts_get",
headers={"x-api-key": os.environ["VOICECHEAP_API_KEY"]},
json={"projectId": "project_launch_2026", "source": "original", "outputFormat": "json", "includeSpeakerLabels": False},
timeout=120,
)
body = response.json()
if not response.ok:
raise RuntimeError(f"{body.get('code')}: {body.get('message')}")
print(body)
{
"data": {
"format": "json",
"transcript": {
"source": "original",
"language": "fr",
"duration": 75,
"text": "Bienvenue au lancement.",
"speakers": [
{
"id": 0,
"label": "Speaker 1"
}
],
"segments": [
{
"index": 0,
"text": "Bienvenue au lancement.",
"begin": 0,
"end": 2,
"duration": 2,
"speaker": 0,
"language": "fr"
}
]
},
"contentType": "application/json"
}
}
Retrieve the original or translated transcript as JSON, SRT or VTT, with optional speaker labels.
Required permissions:
POST https://api.voicecheap.ai/v1/actions/transcripts_get
Authentication and permissions
string
required
Send a VoiceCheap API key in this header. Authorization: Bearer with the same API key is also supported. OAuth access tokens are accepted only by
MCP, not by this REST endpoint.
transcription:read.
An active paid subscription is required. Permissions do not change team roles, resource ownership, media credits, or plan limits.
Parameters
string
required
Text value.Minimum length: 1. Maximum length: 200. Pattern:
^[^/\\]+$.string
Text value.Allowed values: “original”, “translated”. Default: “original”.
string
Text value.Allowed values: “afrikaans”, “albanian”, “amharic”, “arabic”, “armenian”, “assamese”, “azerbaijani”, “basque”, “belarusian”, “bengali”, “bosnian”, “bulgarian”, “catalan”, “croatian”, “czech”, “danish”, “dutch”, “english”, “british english”, “estonian”, “finnish”, “french”, “french canadian”, “galician”, “german”, “greek”, “gujarati”, “hebrew”, “hindi”, “hungarian”, “icelandic”, “indonesian”, “irish”, “italian”, “japanese”, “kannada”, “kazakh”, “khmer”, “korean”, “lao”, “latvian”, “lithuanian”, “macedonian”, “malay”, “malayalam”, “mandarin”, “marathi”, “mongolian”, “nepali”, “norwegian”, “persian”, “polish”, “portuguese”, “brazilian portuguese”, “pt_brazil”, “punjabi”, “romanian”, “russian”, “serbian”, “slovak”, “slovenian”, “spanish”, “swahili”, “swedish”, “tagalog”, “tamil”, “telugu”, “thai”, “turkish”, “ukrainian”, “urdu”, “vietnamese”, “welsh”, “yoruba”, “zulu”.
string
Text value.Allowed values: “json”, “srt”, “vtt”. Default: “json”.
boolean
Boolean value.Default: false.
Complete input schema
Complete input schema
The JSON Schema below preserves the exact field names, nested types, defaults, bounds, and accepted values exposed by discovery. Additional cross-field rules are listed in the operation notes.
{
"type": "object",
"properties": {
"projectId": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"pattern": "^[^/\\\\]+$"
},
"source": {
"default": "original",
"type": "string",
"enum": ["original", "translated"]
},
"targetLanguage": {
"type": "string",
"enum": [
"afrikaans",
"albanian",
"amharic",
"arabic",
"armenian",
"assamese",
"azerbaijani",
"basque",
"belarusian",
"bengali",
"bosnian",
"bulgarian",
"catalan",
"croatian",
"czech",
"danish",
"dutch",
"english",
"british english",
"estonian",
"finnish",
"french",
"french canadian",
"galician",
"german",
"greek",
"gujarati",
"hebrew",
"hindi",
"hungarian",
"icelandic",
"indonesian",
"irish",
"italian",
"japanese",
"kannada",
"kazakh",
"khmer",
"korean",
"lao",
"latvian",
"lithuanian",
"macedonian",
"malay",
"malayalam",
"mandarin",
"marathi",
"mongolian",
"nepali",
"norwegian",
"persian",
"polish",
"portuguese",
"brazilian portuguese",
"pt_brazil",
"punjabi",
"romanian",
"russian",
"serbian",
"slovak",
"slovenian",
"spanish",
"swahili",
"swedish",
"tagalog",
"tamil",
"telugu",
"thai",
"turkish",
"ukrainian",
"urdu",
"vietnamese",
"welsh",
"yoruba",
"zulu"
]
},
"outputFormat": {
"default": "json",
"type": "string",
"enum": ["json", "srt", "vtt"]
},
"includeSpeakerLabels": {
"default": false,
"type": "boolean"
}
},
"required": ["projectId"],
"additionalProperties": false
}
Request examples
Replace example resource identifiers and media keys with values returned for your account. Keep the request identifier stable when retrying the same mutation.curl --request POST 'https://api.voicecheap.ai/v1/actions/transcripts_get' \
--header "x-api-key: $VOICECHEAP_API_KEY" \
--header 'Content-Type: application/json' \
--data '{"projectId":"project_launch_2026","source":"original","outputFormat":"json","includeSpeakerLabels":false}'
const input = {
projectId: 'project_launch_2026',
source: 'original',
outputFormat: 'json',
includeSpeakerLabels: false,
};
const response = await fetch('https://api.voicecheap.ai/v1/actions/transcripts_get', {
method: 'POST',
headers: {
'x-api-key': process.env.VOICECHEAP_API_KEY,
'Content-Type': 'application/json',
},
body: JSON.stringify(input),
});
const body = await response.json();
if (!response.ok) throw new Error(body.code + ': ' + body.message);
console.log(body);
import os
import requests
response = requests.post(
"https://api.voicecheap.ai/v1/actions/transcripts_get",
headers={"x-api-key": os.environ["VOICECHEAP_API_KEY"]},
json={"projectId": "project_launch_2026", "source": "original", "outputFormat": "json", "includeSpeakerLabels": False},
timeout=120,
)
body = response.json()
if not response.ok:
raise RuntimeError(f"{body.get('code')}: {body.get('message')}")
print(body)
Response
A successful first execution returns HTTP 200 with the operation result under data. A replay may return saved request state instead. The example shows one supported response, not every optional field. Returns a formatted transcript object. JSON contains format, transcript and contentType; SRT/VTT also include content and fileExtension.{
"data": {
"format": "json",
"transcript": {
"source": "original",
"language": "fr",
"duration": 75,
"text": "Bienvenue au lancement.",
"speakers": [
{
"id": 0,
"label": "Speaker 1"
}
],
"segments": [
{
"index": 0,
"text": "Bienvenue au lancement.",
"begin": 0,
"end": 2,
"duration": 2,
"speaker": 0,
"language": "fr"
}
]
},
"contentType": "application/json"
}
}
Result fields
| Field | Description |
|---|---|
data.format | json, srt, or vtt. |
data.contentType | application/json, application/x-subrip; charset=utf-8, or text/vtt; charset=utf-8. |
data.content | Subtitle text for srt/vtt only. |
data.fileExtension | srt or vtt for text exports only. |
data.transcript.source | original or translated. |
data.transcript.language | Transcript language. |
data.transcript.duration | Maximum of stored media duration and final segment end, in seconds. |
data.transcript.text | Joined nonempty segment text. |
data.transcript.speakers | Unique speakers sorted by numeric id, with generated Speaker N labels. |
data.transcript.segments | Normalized segments sorted by begin and index, with index, text, begin, end, duration, speaker, language and optional confidence, finalSpeedFactor, words. |
data.transcript.workId | Included for a translated transcript. |
data.transcript.targetLanguage | Included for a translated transcript. |
data.transcript.segments[].begin | Start time in seconds, normalized to three decimal places. |
data.transcript.segments[].end | End time in seconds, normalized to three decimal places. |
data.transcript.segments[].duration | Positive segment duration in seconds. |
data.transcript.segments[].speaker | Zero-based speaker number. |
data.transcript.segments[].finalSpeedFactor | Optional translated-speech duration divided by its segment window, rounded to three decimals; values above 1 indicate speech needed speeding up. |
outputFormat srt; source translated, targetLanguage english, includeSpeakerLabels true.
Returns the translated transcript and SRT content with speaker prefixes.HTTP 200
{
"data": {
"format": "srt",
"transcript": {
"source": "translated",
"language": "english",
"duration": 75,
"text": "Welcome to the product launch.",
"speakers": [
{
"id": 0,
"label": "Speaker 1"
}
],
"segments": [
{
"index": 0,
"text": "Welcome to the product launch.",
"begin": 0,
"end": 2,
"duration": 2,
"speaker": 0,
"language": "english",
"finalSpeedFactor": 1.08
}
],
"workId": "5f8423d1-e4c0-4f80-9e3f-eed959389e24",
"targetLanguage": "english"
},
"content": "1\n00:00:00,000 --> 00:00:02,000\nSpeaker 1: Welcome to the product launch.\n",
"contentType": "application/x-subrip; charset=utf-8",
"fileExtension": "srt"
}
}
outputFormat vtt; source translated, targetLanguage english, includeSpeakerLabels true.
Returns the translated transcript and WEBVTT content with voice labels.HTTP 200
{
"data": {
"format": "vtt",
"transcript": {
"source": "translated",
"language": "english",
"duration": 75,
"text": "Welcome to the product launch.",
"speakers": [
{
"id": 0,
"label": "Speaker 1"
}
],
"segments": [
{
"index": 0,
"text": "Welcome to the product launch.",
"begin": 0,
"end": 2,
"duration": 2,
"speaker": 0,
"language": "english",
"finalSpeedFactor": 1.08
}
],
"workId": "5f8423d1-e4c0-4f80-9e3f-eed959389e24",
"targetLanguage": "english"
},
"content": "WEBVTT\n\n1\n00:00:00.000 --> 00:00:02.000\n<v Speaker 1>Welcome to the product launch.\n",
"contentType": "text/vtt; charset=utf-8",
"fileExtension": "vtt"
}
}
Operation notes
- source defaults to original, outputFormat to json, and includeSpeakerLabels to false. A translated source requires targetLanguage.
- For translated transcripts, the newest language work matching targetLanguage is selected. There is no workId or translatedVersionId input for this action.
- SRT and VTT exports remain JSON action results: content contains the subtitle text, and transcript remains available in the same object. This handler does not return a raw downloadable response.
- includeSpeakerLabels only affects text export cues: SRT uses Speaker N: prefixes and VTT uses voice tags.
- Stored transcript words, when present, expose index, text, speaker and optional confidence; no word-level timestamps are invented. Translated segments may expose finalSpeedFactor when generated speech timing exists.
Usage
Each successful invocation consumes one monthly API/MCP call. Media credits and the operation’s own generation allowances also apply.Errors
| HTTP status | Code | Meaning or recovery |
|---|---|---|
| 400 | CREDENTIAL_IN_QUERY | Credentials were supplied in an access_token or api_key query parameter. Send credentials in headers. |
| 400 | VALIDATION_ERROR | Correct the input using the schema. Invalid or inconsistent values are rejected before execution. |
| 401 | API_KEY_EXPIRED | The API key has expired. |
| 401 | INVALID_API_KEY | Provide a valid, unexpired API key. |
| 401 | INVALID_CREDENTIAL | The Authorization header is malformed or conflicts with x-api-key. |
| 401 | MISSING_CREDENTIAL | No usable header credential was supplied, or it exceeded 4096 characters. |
| 401 | USER_NOT_FOUND | The credential’s account no longer exists. |
| 403 | AMBIGUOUS_TEAM_API_KEY | The credential’s user belongs to more than one team, so the billing context is ambiguous. |
| 403 | FORBIDDEN | The authenticated actor cannot access this project. |
| 403 | INSUFFICIENT_SCOPE | Grant every required permission or choose another credential. |
| 403 | INTEGRATION_PLAN_UNSUPPORTED | The account’s integration limits could not be verified. |
| 403 | SUBSCRIPTION_REQUIRED | Use an active paid subscription. |
| 403 | TEAM_OWNER_NOT_FOUND | The effective team owner account could not be found. |
| 404 | PROJECT_NOT_FOUND | The project does not exist in the accessible account. |
| 404 | TRANSCRIPT_NOT_FOUND | No usable transcript exists for the requested source and target language. |
| 409 | TRANSCRIPT_NOT_READY | The requested original or translated transcript is still processing. |
| 429 | INTEGRATION_MONTHLY_LIMIT_REACHED | Wait for the monthly reset or change plan. |
| 429 | INTEGRATION_RATE_LIMIT_REACHED | Wait for Retry-After when present and use backoff. |
| 500 | INTERNAL_ERROR | Check saved request state and resource history before deciding to retry a mutation. |
| 503 | SERVER_RESTARTING | The server is restarting. Retry shortly and keep the same request identifier for a mutation. |
{
"code": "INSUFFICIENT_SCOPE",
"message": "This credential does not permit the requested action.",
"status": 403,
"details": {
"requiredScopes": ["transcription:read"]
}
}
Was this page helpful?