Music Detection
Music Detection Batch
Classify music and speech in an audio file. Returns frame-level probabilities, a primary label, and percentage breakdowns of content type.
POST
/
api
/
velma-2-music-detection-batch
Detect music and speech in an audio file
curl --request POST \
--url https://platform.modulate.ai/api/velma-2-music-detection-batch \
--header 'Content-Type: multipart/form-data' \
--header 'X-API-Key: <api-key>' \
--form upload_file=@example-fileimport requests
url = "https://platform.modulate.ai/api/velma-2-music-detection-batch"
files = { "upload_file": ("example-file", open("example-file", "rb")) }
headers = {"X-API-Key": "<api-key>"}
response = requests.post(url, files=files, headers=headers)
print(response.text)const form = new FormData();
form.append('upload_file', '<string>');
const options = {method: 'POST', headers: {'X-API-Key': '<api-key>'}};
options.body = form;
fetch('https://platform.modulate.ai/api/velma-2-music-detection-batch', 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://platform.modulate.ai/api/velma-2-music-detection-batch",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Content-Type: multipart/form-data",
"X-API-Key: <api-key>"
],
]);
$response = curl_exec($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://platform.modulate.ai/api/velma-2-music-detection-batch"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-Key", "<api-key>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://platform.modulate.ai/api/velma-2-music-detection-batch")
.header("X-API-Key", "<api-key>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://platform.modulate.ai/api/velma-2-music-detection-batch")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"filename": "my_audio.wav",
"duration_s": 5.76,
"primary_label": "speech",
"music_pct": 0,
"speech_pct": 86.7,
"latency_ms": 1243.5,
"frames": [
{
"start_time_ms": 0,
"end_time_ms": 192,
"music_prob": 0.0213,
"speech_prob": 0.9888
},
{
"start_time_ms": 192,
"end_time_ms": 384,
"music_prob": 0.0204,
"speech_prob": 0.9931
}
]
}Authorizations
API key used for authentication and usage tracking.
Body
multipart/form-data
Audio file to analyse. Must be non-empty. Supported formats:
.3g2, .3ga, .3gp, .3gpp, .8svx, .aa3, .aac,
.ac3, .act, .adts, .aif, .aifc, .aiff, .alac,
.amb, .amr, .ape, .asf, .at3, .au, .avi,
.avr, .awb, .bwf, .c2, .caf, .dss, .dts,
.dtshd, .eac3, .ec3, .f4a, .f4b, .flac, .flv,
.gsm, .iff, .m2a, .m2ts, .m4a, .m4b, .m4r,
.m4v, .mka, .mkv, .mlp, .mmf, .mov, .mp+,
.mp1, .mp2, .mp3, .mp4, .mpa, .mpc, .mpeg,
.mpg, .mpga, .mpp, .mts, .mxf, .nist, .oga,
.ogg, .ogx, .oma, .omg, .opus, .paf, .pvf,
.qcp, .ra, .rf64, .rka, .rm, .rmvb, .sf,
.shn, .snd, .sph, .svx, .tak, .thd,
.ts, .tta, .vob, .voc, .vqf, .w64, .wav,
.wave, .weba, .webm, .wma, .wmv,
.wv. Maximum file size: 100 MB.
Response
Detection completed successfully.
Name of the submitted audio file. Empty string if no filename was provided in the upload.
Example:
"my_audio.wav"
Total duration of the analysed audio in seconds.
Required range:
x >= 0Example:
5.76
Overall classification of the clip:
music- music covers at least as much of the clip as speech, and more than zero.speech- speech covers more of the clip than music, and more than zero.neither- neither music nor speech reached the dominant threshold for any portion of the clip.unknown- no frames could be produced from the audio.
Available options:
music, speech, neither, unknown Example:
"speech"
Percentage of the clip classified as containing music.
Required range:
0 <= x <= 100Example:
0
Percentage of the clip classified as containing speech.
Required range:
0 <= x <= 100Example:
86.7
End-to-end inference time in milliseconds.
Required range:
x >= 0Example:
1243.5
Ordered list of per-frame classification results covering the full duration of the clip.
Show child attributes
Show child attributes
Detect music and speech in an audio file
curl --request POST \
--url https://platform.modulate.ai/api/velma-2-music-detection-batch \
--header 'Content-Type: multipart/form-data' \
--header 'X-API-Key: <api-key>' \
--form upload_file=@example-fileimport requests
url = "https://platform.modulate.ai/api/velma-2-music-detection-batch"
files = { "upload_file": ("example-file", open("example-file", "rb")) }
headers = {"X-API-Key": "<api-key>"}
response = requests.post(url, files=files, headers=headers)
print(response.text)const form = new FormData();
form.append('upload_file', '<string>');
const options = {method: 'POST', headers: {'X-API-Key': '<api-key>'}};
options.body = form;
fetch('https://platform.modulate.ai/api/velma-2-music-detection-batch', 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://platform.modulate.ai/api/velma-2-music-detection-batch",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Content-Type: multipart/form-data",
"X-API-Key: <api-key>"
],
]);
$response = curl_exec($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://platform.modulate.ai/api/velma-2-music-detection-batch"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-Key", "<api-key>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://platform.modulate.ai/api/velma-2-music-detection-batch")
.header("X-API-Key", "<api-key>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://platform.modulate.ai/api/velma-2-music-detection-batch")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"filename": "my_audio.wav",
"duration_s": 5.76,
"primary_label": "speech",
"music_pct": 0,
"speech_pct": 86.7,
"latency_ms": 1243.5,
"frames": [
{
"start_time_ms": 0,
"end_time_ms": 192,
"music_prob": 0.0213,
"speech_prob": 0.9888
},
{
"start_time_ms": 192,
"end_time_ms": 384,
"music_prob": 0.0204,
"speech_prob": 0.9931
}
]
}