Speech to text API for audio and video files

import time, requests

AUTH = "https://rask-prod.auth.us-east-2.amazoncognito.com/oauth2/token"
API  = "https://api.rask.ai"
token = requests.post(AUTH, auth=(CLIENT_ID, CLIENT_SECRET),
                      data={"grant_type": "client_credentials"}).json()["access_token"]
h = {"Authorization": f"Bearer {token}"}

with open("interview.mp3", "rb") as f:
    media = requests.post(f"{API}/api/library/v1/media", headers=h,
                          params={"kind": "audio"}, files={"data": f}).json()
while media["status"] == "processing":
    time.sleep(5)
    media = requests.get(f"{API}/api/library/v1/media/{media['id']}", headers=h).json()

pid = requests.post(f"{API}/v2/projects", headers=h, json={
    "video_id": media["id"], "dst_lang": "es-mx", "num_speakers": 2}).json()["id"]
while requests.get(f"{API}/v2/projects/{pid}", headers=h).json()["status"] != "merging_done":
    time.sleep(10)

# write the source transcript as an .srt file
segments = requests.get(f"{API}/v2/projects/{pid}/transcription", headers=h).json()["segments"]
with open("interview_en.srt", "w") as out:
    for i, s in enumerate(segments, 1):
        out.write(f"{i}\n{s['start']} --> {s['end']}\n{s['speaker']}: {s['src']['text']}\n\n")

// no dependencies, Node 18+ global fetch
const API = 'https://api.rask.ai';
const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
const auth = await fetch('https://rask-prod.auth.us-east-2.amazoncognito.com/oauth2/token', {
  method: 'POST',
  headers: { Authorization: 'Basic ' + btoa(`${CLIENT_ID}:${CLIENT_SECRET}`) },
  body: new URLSearchParams({ grant_type: 'client_credentials' }),
}).then((r) => r.json());
const h = { Authorization: `Bearer ${auth.access_token}`, 'Content-Type': 'application/json' };
const call = (method, path, body) => fetch(API + path, { method, headers: h, body: body && JSON.stringify(body) }).then((r) => r.json());

let media = await call('POST', '/api/library/v1/media/link', { link: 'https://example.com/webinar.mp4' });
while (media.status === 'processing') { await sleep(5000); media = await call('GET', `/api/library/v1/media/${media.id}`); }

let p = await call('POST', '/v2/projects', { video_id: media.id, src_lang: 'en', dst_lang: 'de-de' });
while (p.status !== 'merging_done') { await sleep(10000); p = await call('GET', `/v2/projects/${p.id}`); }

const { segments } = await call('GET', `/v2/projects/${p.id}/transcription`);
segments.forEach((s) => console.log(`[${s.start}] ${s.speaker}: ${s.src.text}`));
console.log(p.translation_vtt_path);   // German subtitles for your player

# 1. token (valid 1 hour - cache and reuse it)
TOKEN=$(curl -s -X POST https://rask-prod.auth.us-east-2.amazoncognito.com/oauth2/token \
  -u "$CLIENT_ID:$CLIENT_SECRET" -d "grant_type=client_credentials" | jq -r .access_token)

# 2. upload a local audio file
MEDIA_ID=$(curl -s -X POST "https://api.rask.ai/api/library/v1/media?kind=audio" \
  -H "Authorization: Bearer $TOKEN" -F "data=@podcast_episode.mp3" | jq -r .id)

# 3. create the project once the media status is ready
ID=$(curl -s -X POST https://api.rask.ai/v2/projects \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -d "{\"video_id\": \"$MEDIA_ID\", \"dst_lang\": \"fr-fr\"}" | jq -r .id)

# 4. when status is merging_done, read the transcript with speaker labels
curl -s https://api.rask.ai/v2/projects/$ID/transcription -H "Authorization: Bearer $TOKEN" \
  | jq -r '.segments[] | "\(.start) \(.speaker): \(.src.text)"'

<?php
use GuzzleHttp\Client;

$http = new Client(['base_uri' => 'https://api.rask.ai']);
$json = fn($r) => json_decode($r->getBody(), true);
$auth = $json((new Client)->post('https://rask-prod.auth.us-east-2.amazoncognito.com/oauth2/token',
    ['auth' => [$clientId, $clientSecret], 'form_params' => ['grant_type' => 'client_credentials']]));
$h = ['Authorization' => 'Bearer ' . $auth['access_token']];

$media = $json($http->post('/api/library/v1/media/link', ['headers' => $h, 'json' => [
    'link' => 'https://example.com/interview.mp3']]));
while ($media['status'] === 'processing') {
    sleep(5);
    $media = $json($http->get("/api/library/v1/media/{$media['id']}", ['headers' => $h]));
}

$p = $json($http->post('/v2/projects', ['headers' => $h, 'json' => [
    'video_id' => $media['id'], 'dst_lang' => 'es-mx']]));
while ($p['status'] !== 'merging_done') {
    sleep(10);
    $p = $json($http->get("/v2/projects/{$p['id']}", ['headers' => $h]));
}

$t = $json($http->get("/v2/projects/{$p['id']}/transcription", ['headers' => $h]));
foreach ($t['segments'] as $s) {
    echo $s['start'], ' ', $s['speaker'], ': ', $s['src']['text'], PHP_EOL;
}