Frame Synthesis

Perform singing voice synthesis.

Laravel Implementation Status: ✅ Fully supported by Core (fallback implemented)

POST /frame_synthesis

Frame Synthesis

cURL

curl --request POST \
  --url https://api.example.com/frame_synthesis \
  --header 'Content-Type: application/json' \
  --data '
{
  "f0": [
    123
  ],
  "volume": [
    123
  ],
  "phonemes": [
    {
      "phoneme": "<string>",
      "frame_length": 123,
      "note_id": "<string>"
    }
  ],
  "volumeScale": 123,
  "outputSamplingRate": 123,
  "outputStereo": true
}
'

import requests

url = "https://api.example.com/frame_synthesis"

payload = {
    "f0": [123],
    "volume": [123],
    "phonemes": [
        {
            "phoneme": "<string>",
            "frame_length": 123,
            "note_id": "<string>"
        }
    ],
    "volumeScale": 123,
    "outputSamplingRate": 123,
    "outputStereo": True
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    f0: [123],
    volume: [123],
    phonemes: [{phoneme: '<string>', frame_length: 123, note_id: '<string>'}],
    volumeScale: 123,
    outputSamplingRate: 123,
    outputStereo: true
  })
};

fetch('https://api.example.com/frame_synthesis', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/frame_synthesis",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'f0' => [
        123
    ],
    'volume' => [
        123
    ],
    'phonemes' => [
        [
                'phoneme' => '<string>',
                'frame_length' => 123,
                'note_id' => '<string>'
        ]
    ],
    'volumeScale' => 123,
    'outputSamplingRate' => 123,
    'outputStereo' => true
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/frame_synthesis"

	payload := strings.NewReader("{\n  \"f0\": [\n    123\n  ],\n  \"volume\": [\n    123\n  ],\n  \"phonemes\": [\n    {\n      \"phoneme\": \"<string>\",\n      \"frame_length\": 123,\n      \"note_id\": \"<string>\"\n    }\n  ],\n  \"volumeScale\": 123,\n  \"outputSamplingRate\": 123,\n  \"outputStereo\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/frame_synthesis")
  .header("Content-Type", "application/json")
  .body("{\n  \"f0\": [\n    123\n  ],\n  \"volume\": [\n    123\n  ],\n  \"phonemes\": [\n    {\n      \"phoneme\": \"<string>\",\n      \"frame_length\": 123,\n      \"note_id\": \"<string>\"\n    }\n  ],\n  \"volumeScale\": 123,\n  \"outputSamplingRate\": 123,\n  \"outputStereo\": true\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/frame_synthesis")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"f0\": [\n    123\n  ],\n  \"volume\": [\n    123\n  ],\n  \"phonemes\": [\n    {\n      \"phoneme\": \"<string>\",\n      \"frame_length\": 123,\n      \"note_id\": \"<string>\"\n    }\n  ],\n  \"volumeScale\": 123,\n  \"outputSamplingRate\": 123,\n  \"outputStereo\": true\n}"

response = http.request(request)
puts response.read_body

200

"<string>"

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Paramètres de requête

speaker · integer · requis

core_version · string

Corps

application/json

Frame-by-frame query for speech synthesis.

f0 · number[] · requis

Frame-by-frame fundamental frequency

volume · number[] · requis

Frame-by-frame volume

phonemes · FramePhoneme · object[] · requis

List of phonemes

Show child attributes

volumeScale · number · requis

Overall volume

outputSamplingRate · integer · requis

Output sampling rate of the audio data

outputStereo · boolean · requis

Whether to output audio data in stereo

Réponse

200

audio/wav

Successful Response

The response is of type file.