curl --request POST \
--url https://pria.praxislxp.com/api/user/transcribe \
--header 'Content-Type: multipart/form-data' \
--header 'x-access-token: <api-key>' \
--form audio='@example-file' \
--form 'language=<string>'import requests
url = "https://pria.praxislxp.com/api/user/transcribe"
files = { "audio": ("example-file", open("example-file", "rb")) }
payload = { "language": "<string>" }
headers = {"x-access-token": "<api-key>"}
response = requests.post(url, data=payload, files=files, headers=headers)
print(response.text)const form = new FormData();
form.append('audio', '<string>');
form.append('language', '<string>');
const options = {method: 'POST', headers: {'x-access-token': '<api-key>'}};
options.body = form;
fetch('https://pria.praxislxp.com/api/user/transcribe', 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://pria.praxislxp.com/api/user/transcribe",
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=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Content-Type: multipart/form-data",
"x-access-token: <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://pria.praxislxp.com/api/user/transcribe"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-access-token", "<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://pria.praxislxp.com/api/user/transcribe")
.header("x-access-token", "<api-key>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://pria.praxislxp.com/api/user/transcribe")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-access-token"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"success": true,
"transcript": "<string>",
"provider": "<string>",
"durationMs": 123
}{
"success": false,
"message": "Rate limit: 30/min",
"retryAfterMs": 123
}Transient speech-to-text
Accepts a single audio blob, dispatches it to the user’s institution-
configured STT provider via getProviderForModel(user, 'audioAnalysisModel'),
and returns the transcript. Suitable for in-place dictation (e.g. the
chat textarea mic icon) — explicitly does NOT persist Upload,
History, or embedding rows.
Rate-limited 30 req / 60s / user (per-process token bucket). The
gate also enforces the same checkAudioNotesAllowed predicate the
/audio-notes route uses (guest mode + institutional opt-out).
Accepted mimetypes: audio/webm, audio/ogg, audio/mp4,
audio/mpeg, audio/wav. 25 MB ceiling covers ~120s of opus at
128 kbps with headroom.
curl --request POST \
--url https://pria.praxislxp.com/api/user/transcribe \
--header 'Content-Type: multipart/form-data' \
--header 'x-access-token: <api-key>' \
--form audio='@example-file' \
--form 'language=<string>'import requests
url = "https://pria.praxislxp.com/api/user/transcribe"
files = { "audio": ("example-file", open("example-file", "rb")) }
payload = { "language": "<string>" }
headers = {"x-access-token": "<api-key>"}
response = requests.post(url, data=payload, files=files, headers=headers)
print(response.text)const form = new FormData();
form.append('audio', '<string>');
form.append('language', '<string>');
const options = {method: 'POST', headers: {'x-access-token': '<api-key>'}};
options.body = form;
fetch('https://pria.praxislxp.com/api/user/transcribe', 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://pria.praxislxp.com/api/user/transcribe",
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=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Content-Type: multipart/form-data",
"x-access-token: <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://pria.praxislxp.com/api/user/transcribe"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-access-token", "<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://pria.praxislxp.com/api/user/transcribe")
.header("x-access-token", "<api-key>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://pria.praxislxp.com/api/user/transcribe")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-access-token"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"success": true,
"transcript": "<string>",
"provider": "<string>",
"durationMs": 123
}{
"success": false,
"message": "Rate limit: 30/min",
"retryAfterMs": 123
}Authorizations
JWT token passed in x-access-token header
Body
Response
Transcript returned.
true
The recognised text. Empty string on silent input.
Resolved STT provider id (one of mistral_cli, openai_cli, bedrock_cli, anthropic_cli, google_genai_cli, xai_cli).
Audio duration in milliseconds when the provider returns it (openai). Null when not reported (mistral).
Was this page helpful?