curl --request POST \
--url https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/audio/transcriptions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form file=@example-fileconst form = new FormData();
form.append('file', '<string>');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/audio/transcriptions', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/audio/transcriptions"
files = { "file": ("example-file", open("example-file", "rb")) }
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, files=files, headers=headers)
print(response.text){
"text": "<string>",
"usage": {}
}{
"error": "<string>",
"message": "<string>",
"code": "<string>",
"details": {},
"status": 123,
"retryAfter": 123,
"provider": "<string>",
"model": "<string>",
"provider_error_type": "<string>"
}{
"error": "<string>",
"message": "<string>",
"code": "<string>",
"details": {},
"status": 123,
"retryAfter": 123,
"provider": "<string>",
"model": "<string>",
"provider_error_type": "<string>"
}{
"error": "<string>",
"message": "<string>",
"code": "<string>",
"details": {},
"status": 123,
"retryAfter": 123,
"provider": "<string>",
"model": "<string>",
"provider_error_type": "<string>"
}{
"error": "<string>",
"message": "<string>",
"code": "<string>",
"details": {},
"status": 123,
"retryAfter": 123,
"provider": "<string>",
"model": "<string>",
"provider_error_type": "<string>"
}{
"error": "<string>",
"message": "<string>",
"code": "<string>",
"details": {},
"status": 123,
"retryAfter": 123,
"provider": "<string>",
"model": "<string>",
"provider_error_type": "<string>"
}Transcribe audio into text
OpenAI-compatible speech-to-text endpoint: an OpenAI SDK pointed at
this gateway calls it unchanged. The audio is sent as a multipart
file part, held in memory only and never stored.
model defaults to the organization’s transcription model, then to
the platform default. srt and vtt response formats are not
supported; text is answered as text/plain, ended by a newline like
OpenAI (a silent recording is "\n"). A file sent with a generic MIME
type (application/octet-stream) is named after its original extension.
Requires the llm-gateway:models:audio-transcriptions permission.
Governance overlays may reject the model (403 MODEL_NOT_ALLOWED).
curl --request POST \
--url https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/audio/transcriptions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form file=@example-fileconst form = new FormData();
form.append('file', '<string>');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/audio/transcriptions', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/audio/transcriptions"
files = { "file": ("example-file", open("example-file", "rb")) }
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, files=files, headers=headers)
print(response.text){
"text": "<string>",
"usage": {}
}{
"error": "<string>",
"message": "<string>",
"code": "<string>",
"details": {},
"status": 123,
"retryAfter": 123,
"provider": "<string>",
"model": "<string>",
"provider_error_type": "<string>"
}{
"error": "<string>",
"message": "<string>",
"code": "<string>",
"details": {},
"status": 123,
"retryAfter": 123,
"provider": "<string>",
"model": "<string>",
"provider_error_type": "<string>"
}{
"error": "<string>",
"message": "<string>",
"code": "<string>",
"details": {},
"status": 123,
"retryAfter": 123,
"provider": "<string>",
"model": "<string>",
"provider_error_type": "<string>"
}{
"error": "<string>",
"message": "<string>",
"code": "<string>",
"details": {},
"status": 123,
"retryAfter": 123,
"provider": "<string>",
"model": "<string>",
"provider_error_type": "<string>"
}{
"error": "<string>",
"message": "<string>",
"code": "<string>",
"details": {},
"status": 123,
"retryAfter": 123,
"provider": "<string>",
"model": "<string>",
"provider_error_type": "<string>"
}Authorizations
User-bound credential carrying an identity: either a session JWT
or a user access token (at:*) generated from the user settings UI.
Send as Authorization: Bearer <token>.
Org API keys (iak_*) are not accepted here - they carry
no user identity. Use the x-prismeai-api-key header instead
(see OrgApiKeyAuth).
Body
Audio file (webm, mp4, m4a, mp3, ogg, wav, flac), 25 MB max by default.
256ISO-639-1 language of the audio (e.g. fr). Detected when omitted.
Text to guide the transcription (vocabulary, previous segment).
json, text, verbose_json Was this page helpful?