Text To Speech

Speech To Text using the openai/whisper AI Model.

POST v1/replicate/stt

Text To Speech

cURL

curl --request POST \
  --url http://localhost:9000/api/v1/replicate/stt \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form temperature=123 \
  --form translate=true \
  --form 'initial_prompt=<string>' \
  --form condition_on_previous_text=true \
  --form audio='@example-file'

import requests

url = "http://localhost:9000/api/v1/replicate/stt"

files = { "audio": ("example-file", open("example-file", "rb")) }
payload = {
    "temperature": "123",
    "translate": "true",
    "initial_prompt": "<string>",
    "condition_on_previous_text": "true"
}
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('temperature', '123');
form.append('translate', 'true');
form.append('initial_prompt', '<string>');
form.append('condition_on_previous_text', 'true');
form.append('audio', '{
  "fileName": "example-file"
}');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('http://localhost:9000/api/v1/replicate/stt', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_PORT => "9000",
  CURLOPT_URL => "http://localhost:9000/api/v1/replicate/stt",
  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=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"translate\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"initial_prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"condition_on_previous_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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 := "http://localhost:9000/api/v1/replicate/stt"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"translate\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"initial_prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"condition_on_previous_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("http://localhost:9000/api/v1/replicate/stt")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"translate\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"initial_prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"condition_on_previous_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("http://localhost:9000/api/v1/replicate/stt")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"translate\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"initial_prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"condition_on_previous_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--"

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

Query

model · string · default: "openai/whisper" · required

The model to be used;

Body

audio · file · required

Audio file

temperature · float · default: "0.0"

temperature to use for sampling

translate · boolean · default: "False"

Translate the text to English when set to True

initial_prompt · string

optional text to provide as a prompt for the first window.

condition_on_previous_text · boolean · default: "True"

if True, provide the previous output of the model as a prompt for the next window; disabling may make the text inconsistent across windows, but the model becomes less prone to getting stuck in a failure loop.