Text to speech synthesis
speech/synthesis@1.0.12 providers
Text to speech synthesis
Convert text into speech synchronously.
Input
Text
Voice
Audio
Result
Audio content
1.Choose a provider
2.Use TextToSpeechSynthesis with mock in your code
Below instructions are for our Node.js SDK. Use OneService for other languages.
npm i @superfaceai/one-sdk
Copied!
const { SuperfaceClient } = require('@superfaceai/one-sdk');
// You can manage tokens here: https://superface.ai/insights
const sdk = new SuperfaceClient({ sdkAuthToken: '<< Login to get your token >>' });
async function run() {
// Load the profile
const profile = await sdk.getProfile('speech/synthesis@1.0.1');
// Use the profile
const result = await profile
.getUseCase('TextToSpeechSynthesis')
.perform({
text: 'Hello world.',
voice: {
languageCode: 'en-US'
},
audio: {
encoding: 'linear_pcm'
}
}, {
provider: 'mock'
});
// Handle the result
try {
const data = result.unwrap();
console.log(data);
} catch (error) {
console.error(error);
}
}
run();Copied!
Structure details
Input (object)
text
required
The text input to be synthesized.
string
voice
required
Voice selection options.
object
languageCode
required
The language (and potentially also the region) of the voice expressed as a BCP-47 language tag, e.g. 'en-US'.
string
name
optional
The name of the voice.
string
audio
required
Audio format options.
object
encoding
required
The format of the audio byte stream.
enum
mp3linear_pcm
sampleRateHertz
optional
The synthesis sample rate in hertz for the audio. Selected sample rate has to be supported by selected audio encoding format.
number
Example
{
"text": "Hello world.",
"voice": {
"languageCode": "en-US"
},
"audio": {
"encoding": "linear_pcm"
}
}Copied!
Result (object)
audioContent
required
Synthesised audio data bytes encoded as specified in the audio options input.
Example
{
"audioContent": "<Synthesised audio data bytes encoded as 16-bit signed little-endian samples with WAV header>"
}Copied!