Skip to main content
POST

Limits

To translate speech into English, send the same form to POST /v1/audio/translations, without language.

Authorizations

x-api-key
string
header
required

Your ZeroGPU API key. Create one in the dashboard under API keys. Send it on every request.

Body

multipart/form-data
file
file
required

The audio file to transcribe.

model
enum<string>
default:whisper-tiny

Model identifier. The endpoint serves whisper-tiny.

Available options:
whisper-tiny
Example:

"whisper-tiny"

language
string

ISO-639-1 code, such as en. Detected automatically when omitted.

Example:

"en"

prompt
string

Text to guide spelling and style, such as names or jargon.

Maximum string length: 4096
response_format
enum<string>
default:json

json and verbose_json return application/json; text, srt, and vtt return text/plain.

Available options:
json,
text,
srt,
verbose_json,
vtt
temperature
number
default:0

Sampling temperature.

Required range: 0 <= x <= 1
timestamp_granularities[]
enum<string>[]

segment (default), word, or both. Requires verbose_json.

Available options:
segment,
word

Response

The transcript, in the requested response_format.

json returns { text }. verbose_json adds task, language, duration, and segments and/or words.

text
string
required

The transcript.