POST
/
v1
/
ai
/
speech
/
bytes
Generate speech (binary stream)
curl --request POST \
  --url https://api.lmnt.com/v1/ai/speech/bytes \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '{
  "voice": "ava",
  "text": "hello world.",
  "model": "blizzard",
  "language": "auto",
  "format": "mp3",
  "sample_rate": 24000,
  "seed": 123,
  "top_p": 0.8,
  "temperature": 1
}'
This response does not have an example.
Want to stream timestamps with your speech? Check out the streaming WebSocket endpoint and examples using the SDKs in the synchronizing timing guide.

Authorizations

​
X-API-Key
string
header
required

Your API key; get it from your LMNT account page.

Body

application/json

Response

200
application/octet-stream

OK

The response is of type file.