POST
/
v1
/
ai
/
speech
curl --request POST \
  --url https://api.lmnt.com/v1/ai/speech \
  --header 'Content-Type: multipart/form-data' \
  --header 'X-API-Key: <api-key>' \
  --form voice=ava \
  --form 'text=hello world.' \
  --form model=aurora \
  --form language=en \
  --form format=mp3 \
  --form sample_rate=24000 \
  --form speed=1 \
  --form seed=123 \
  --form conversational=false \
  --form length=123 \
  --form top_p=1 \
  --form temperature=1 \
  --form return_durations=true
{
  "audio": "<string>",
  "durations": [
    {
      "text": "<string>",
      "duration": 123,
      "start": 123
    }
  ],
  "seed": 123
}

The output of this POST request is a JSON object from which you must extract and decode the base64-encoded audio data. Here is an example of how to do so in your terminal:

jq -r '.audio' lmnt-output.json | base64 --decode > lmnt-audio-output.mp3

The file format of your audio output depends on the format specified in the inital request (this example assumes format=mp3).

Authorizations

​
X-API-Key
string
header
required

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

Body

multipart/form-data
​
voice
string
required

The voice id of the voice to use for synthesis; voice ids can be retrieved by calls to List voices or Voice info

​
text
string
required

The text to synthesize; max 5000 characters per request (including spaces)

​
model
enum<string>
default:
aurora

The model to use for synthesis. One of aurora (default) or blizzard. Learn more about models here.

Available options:
aurora,
blizzard
​
language
enum<string>
default:
en

The desired language of the synthesized speech. Two letter ISO 639-1 code. Does not work with professional clones and the blizzard model.

Available options:
de,
en,
es,
fr,
pt,
zh,
ko,
hi
​
format
enum<string>
default:
mp3

The file format of the synthesized audio output

Available options:
aac,
mp3,
mulaw,
raw,
wav
​
sample_rate
enum<number>
default:
24000

The desired output sample rate in Hz

Available options:
8000,
16000,
24000
​
speed
number
default:
1

The talking speed of the generated speech, a floating point value between 0.25 (slow) and 2.0 (fast).

Required range: 0.25 < x < 2
​
seed
integer

Seed used to specify a different take; defaults to random

​
conversational
boolean
default:
false

Set this to true to generate conversational-style speech rather than reading-style speech. Does not work with the blizzard model.

​
length
number

Produce speech of this length in seconds; maximum 300.0 (5 minutes). Does not work with the blizzard model.

Required range: x < 300
​
top_p
number
default:
1

Controls the stability of the generated speech. A lower value (like 0.3) produces more consistent, reliable speech. A higher value (like 0.9) gives more flexibility in how words are spoken, but might occasionally produce unusual intonations or speech patterns.

Required range: 0 < x < 1
​
temperature
number
default:
1

Influences how expressive and emotionally varied the speech becomes. Lower values (like 0.3) create more neutral, consistent speaking styles. Higher values (like 1.0) allow for more dynamic emotional range and speaking styles.

Required range: x > 0
​
return_durations
boolean
default:
false

If set as true, response will contain a durations object.

Response

200
application/json
OK
​
audio
string
required

The base64-encoded audio file; the format is determined by the format parameter.

​
seed
integer
required

The seed used to generate this speech; can be used to replicate this output take (assuming the same text is resynthsized with this seed number, see here for more details).

​
durations
object[]

A JSON object outlining the spoken duration of each synthesized input element (words and non-words like spaces, punctuation, etc.). See an example of this object for the input string "Hello world!"

Was this page helpful?

Generate speechGenerate speech (simple)