Aligner 1 aligner-1

Times the words of a text in the audio that holds them: a start, an end and a confidence for every word and line, for songs and for speech.

From the live catalog

View .md

Input

$0.0000333 / second

region ATL

Limits

What one subscription may send this model. Limits says what happens past them.

Requests a minute	At once
30	5

Inputs

Input	Accepts
`audio`	formats wav, mpeg max length 900 seconds max size 25 MB
`text`	max prompt 12K characters

Parameters

Does not stream.

Parameter	Type	Values	Default
`mode`	string	lyrics, speech	`lyrics`
`language`	string	af, ca, cs, cy, da, de, en, es, et, eu, fi, fr, ga, gl, hr, hu, id, is, it, lt, lv, ms, nl, no, pl, pt, ro, sk, sl, sq, sv, sw, tl, tr

Endpoints

POST/v1/audio/alignments Create Alignment

A request

curl https://api.vultrinference.com/v1/audio/alignments \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY" \
  -F "model=aligner-1" \
  -F "file=@file.pdf" \
  -F "text=string"

import os
import requests

response = requests.post(
    "https://api.vultrinference.com/v1/audio/alignments",
    headers={"Authorization": f"Bearer {os.environ['VULTR_INFERENCE_API_KEY']}"},
    files={"file": open("file.pdf", "rb")},
    data={
    "model": "aligner-1",
    "text": "string",
},
)
print(response.json())

import { openAsBlob } from "node:fs";

const form = new FormData();
form.append("model", "aligner-1");
form.append("file", await openAsBlob("file.pdf"), "file.pdf");
form.append("text", "string");

const response = await fetch("https://api.vultrinference.com/v1/audio/alignments", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VULTR_INFERENCE_API_KEY}`,
  },
  body: form,
});
console.log(await response.json());