Synthesize speech
Synthesizes speech from a text string and provides advanced information about the synthesis. Returns a JSON object that contains a base64-encoded audio file, the seed used in speech generation, and optionally an object detailing the duration of each spoken word.
Specify either speed or length, not both; otherwise a request with both will result in an 500 server error as the desired speed might not match the desired length.
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).
Headers
Your API key; get it from your LMNT account page.
Body
The voice id of the voice to use for synthesis; voice ids can be retrieved by calls to List voices or Voice info
The text to synthesize; max 5000 characters per request (including spaces).
The file format of the synthesized audio output, either aac, mp3, mulaw, raw, wav; defaults to mp3.
The desired language of the synthesized speech. Two letter ISO 639-1 code. One of de, en, es, fr, pt, zh, ko, hi. Does not work with professional clones.
Set this to true to generate conversational-style speech rather than reading-style speech; defaults to false.
The desired output sample rate in Hz, one of: 8000, 16000, 24000; defaults to 24000 for all formats except mulaw which defaults to 8000.
The talking speed of the generated speech, a floating point value between 0.25 (slow) and 2.0 (fast); defaults to 1.0.
Produce speech of this length in seconds; maximum 300.0 (5 minutes).
If set as true, response will contain a durations object; see definition in the response section below.
Seed used to specify a different take; defaults to random (see here for more details).
Response
The base64-encoded audio file; the format is determined by the format parameter.
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).
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?