cURL
curl https://compute.prentis.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $PRENTIS_API_KEY" \
-F file=@recording.wav \
-F model=accounts/<your-account>/deployments/<your-asr-deployment> \
-F language=enimport os
from openai import OpenAI
client = OpenAI(base_url="https://compute.prentis.ai/v1", api_key=os.environ["PRENTIS_API_KEY"])
with open("recording.wav", "rb") as f:
resp = client.audio.transcriptions.create(
model="accounts/<your-account>/deployments/<your-asr-deployment>",
file=f,
language="en",
)
print(resp.text)import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://compute.prentis.ai/v1",
apiKey: process.env.PRENTIS_API_KEY,
});
const resp = await client.audio.transcriptions.create({
model: "accounts/<your-account>/deployments/<your-asr-deployment>",
file: fs.createReadStream("recording.wav"),
language: "en",
});
console.log(resp.text);const form = new FormData();
form.append('file', '<string>');
form.append('model', 'accounts/acme/deployments/asr-voice-01');
form.append('language', '<string>');
form.append('prompt', '<string>');
form.append('temperature', '0.5');
form.append('response_format', 'json');
form.append('stream', 'false');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://compute.prentis.ai/v1/audio/transcriptions', 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://compute.prentis.ai/v1/audio/transcriptions",
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=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\naccounts/acme/deployments/asr-voice-01\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: multipart/form-data; boundary=---011000010111000001101001"
],
]);
$response = curl_exec($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://compute.prentis.ai/v1/audio/transcriptions"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\naccounts/acme/deployments/asr-voice-01\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://compute.prentis.ai/v1/audio/transcriptions")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\naccounts/acme/deployments/asr-voice-01\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://compute.prentis.ai/v1/audio/transcriptions")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\naccounts/acme/deployments/asr-voice-01\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"text": "Can you move my three o'clock meeting to Thursday morning?",
"usage": {
"type": "duration",
"seconds": 4
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}Inference
Audio transcriptions
Turn a WAV recording into text on one of your dedicated speech-to-text deployments. Shaped like OpenAI’s audio transcriptions, so an OpenAI SDK’s audio.transcriptions.create works by changing base_url alone. The deployment is billed for the GPU time it holds; the call itself is not billed.
POST
/
audio
/
transcriptions
cURL
curl https://compute.prentis.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $PRENTIS_API_KEY" \
-F file=@recording.wav \
-F model=accounts/<your-account>/deployments/<your-asr-deployment> \
-F language=enimport os
from openai import OpenAI
client = OpenAI(base_url="https://compute.prentis.ai/v1", api_key=os.environ["PRENTIS_API_KEY"])
with open("recording.wav", "rb") as f:
resp = client.audio.transcriptions.create(
model="accounts/<your-account>/deployments/<your-asr-deployment>",
file=f,
language="en",
)
print(resp.text)import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://compute.prentis.ai/v1",
apiKey: process.env.PRENTIS_API_KEY,
});
const resp = await client.audio.transcriptions.create({
model: "accounts/<your-account>/deployments/<your-asr-deployment>",
file: fs.createReadStream("recording.wav"),
language: "en",
});
console.log(resp.text);const form = new FormData();
form.append('file', '<string>');
form.append('model', 'accounts/acme/deployments/asr-voice-01');
form.append('language', '<string>');
form.append('prompt', '<string>');
form.append('temperature', '0.5');
form.append('response_format', 'json');
form.append('stream', 'false');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://compute.prentis.ai/v1/audio/transcriptions', 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://compute.prentis.ai/v1/audio/transcriptions",
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=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\naccounts/acme/deployments/asr-voice-01\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: multipart/form-data; boundary=---011000010111000001101001"
],
]);
$response = curl_exec($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://compute.prentis.ai/v1/audio/transcriptions"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\naccounts/acme/deployments/asr-voice-01\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://compute.prentis.ai/v1/audio/transcriptions")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\naccounts/acme/deployments/asr-voice-01\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://compute.prentis.ai/v1/audio/transcriptions")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\naccounts/acme/deployments/asr-voice-01\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"stream\"\r\n\r\nfalse\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"text": "Can you move my three o'clock meeting to Thursday morning?",
"usage": {
"type": "duration",
"seconds": 4
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"code": "INVALID_API_KEY",
"param": "<string>"
}
}Which models accept this
Only a dedicated deployment of a model that transcribes, named in full asaccounts/<account>/deployments/<deployment>. A bare model name returns
MODEL_CAPABILITY_UNSUPPORTED.
WAV only
file must be a WAV with PCM samples (16, 24 or 32-bit), up to 25 MB and 10 minutes. Other
formats return MEDIA_UNSUPPORTED; a longer or larger file returns 413 MEDIA_TOO_LARGE.Authorizations
Authorization: Bearer <your API key>. On /v1/messages, the Anthropic-style x-api-key: <your API key> header is accepted instead.
Body
multipart/form-data
The audio to transcribe: a WAV file (PCM, 16, 24 or 32-bit), up to 25 MB and 10 minutes. Other formats return MEDIA_UNSUPPORTED.
The speech-to-text deployment that transcribes the audio, accounts/{account}/deployments/{deployment}. A model name, or a deployment of a model that does not transcribe, returns MODEL_CAPABILITY_UNSUPPORTED.
Example:
"accounts/acme/deployments/asr-voice-01"
The language spoken, as an ISO-639-1 code such as en or zh. Leave it out and the model detects it.
Text that tells the model what it is about to hear: names, product terms, the spelling you expect. UTF-8 text, up to 64 KB.
Randomness when picking each word. 0 is the most repeatable and the usual choice for transcription.
Required range:
0 <= x <= 1json (the default) returns an object with text and usage; text returns the transcript as plain text. Timestamped formats (verbose_json, srt, vtt) are not supported.
Available options:
json, text Return the transcript as server-sent events as it is recognised, instead of one response at the end. The final event carries the full text and the usage.
Response
OK. With stream: true the same call answers text/event-stream instead: data-only events, a transcript.text.delta for each new piece of text, then one transcript.text.done with the full text and the usage, which ends the stream. There is no [DONE] line.