Skip to main content
POST
/
post
/
speech
/
asr
cURL
curl -L -X POST https://api.gradium.ai/api/post/speech/asr \
  -H "x-api-key: your_api_key" \
  -H "Content-Type: audio/wav" \
  --data-binary @input.wav
"<string>"

Documentation Index

Fetch the complete documentation index at: https://docs.gradium.ai/llms.txt

Use this file to discover all available pages before exploring further.

Headers

​
x-api-key
string
required

Your Gradium API key

​
Content-Type
enum<string>

Format of the audio in the request body. Defaults to audio/wav when omitted.

Available options:
audio/wav,
audio/pcm,
audio/ogg,
audio/opus

Query Parameters

​
model
string
default:default

Speech-to-Text model name.

​
input_format
enum<string>

Overrides the audio format detected from Content-Type.

Available options:
wav,
pcm,
opus
​
json_config
string

JSON-encoded model configuration. Example: {"language": "en"}

Body

WAV audio file.

Response

NDJSON stream of transcription messages.

Newline-delimited JSON messages: text, end_text, or error. The body closes when transcription is complete.