Text to speech API for video voiceover

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}"}

def wait(pid):
    while (p := requests.get(f"{API}/v2/projects/{pid}", headers=h).json())["status"] != "merging_done":
        time.sleep(10)
    return p

script = requests.post(f"{API}/v2/transcriptions", headers=h, json={"segments": [
        {"speaker": "SPEAKER_00", "start": "00:00:00,500", "end": "00:00:04,800",
         "src": {"text": "Welcome to the new dashboard.", "lang": "en"},
         "dst": {"text": "Bienvenido al nuevo panel.", "lang": "es-mx"}},
    ]}).json()

pid = requests.post(f"{API}/v2/projects", headers=h, json={
    "video_id": VIDEO_ID, "dst_lang": "es-mx", "transcript_id": script["id"]}).json()["id"]
project = wait(pid)

voices = requests.get(f"{API}/v2/projects/{pid}/voices", headers=h).json()
preset = next(v for v in voices if v["gender"] == "female")
requests.patch(f"{API}/v2/projects/{pid}", headers=h,
               json={"voice": {**project["voice"], "SPEAKER_00": preset["id"]}})
requests.post(f"{API}/v2/projects/{pid}/generate", headers=h)
print(wait(pid)["voiceover"])

// 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 ${auth.access_token}`, 'Content-Type': 'application/json' };
const call = (method, path, body) => fetch(API + path, { method, headers: h, body: body && JSON.stringify(body) }).then((r) => r.json());
const wait = async (id) => { let p; while ((p = await call('GET', `/v2/projects/${id}`)).status !== 'merging_done') await sleep(10000); return p; };

const script = await call('POST', '/v2/transcriptions', { segments: [
  { speaker: 'SPEAKER_00', start: '00:00:00,500', end: '00:00:04,800',
    src: { text: 'Welcome to the new dashboard.', lang: 'en' },
    dst: { text: 'Bienvenido al nuevo panel.', lang: 'es-mx' } },
] });

const { id } = await call('POST', '/v2/projects', { video_id: VIDEO_ID, dst_lang: 'es-mx', transcript_id: script.id });
const project = await wait(id);

const voices = await call('GET', `/v2/projects/${id}/voices`);
const preset = voices.find((v) => v.gender === 'female');
await call('PATCH', `/v2/projects/${id}`, { voice: { ...project.voice, SPEAKER_00: preset.id } });
await call('POST', `/v2/projects/${id}/generate`);
console.log((await wait(id)).voiceover);

# 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. your script as an SRT file in the target language
TRANSCRIPT_ID=$(curl -s -X POST "https://api.rask.ai/v2/transcriptions/srt?dst_lang=es-mx" \
  -H "Authorization: Bearer $TOKEN" -F "dst=@script_es-mx.srt" | jq -r .id)

# 3. voice it over the video
ID=$(curl -s -X POST https://api.rask.ai/v2/projects \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -d "{\"video_id\": \"$VIDEO_ID\", \"dst_lang\": \"es-mx\", \"transcript_id\": \"$TRANSCRIPT_ID\"}" | jq -r .id)

# 4. when status is merging_done, read the voiceover links
curl -s https://api.rask.ai/v2/projects/$ID -H "Authorization: Bearer $TOKEN" \
  | jq '{status, voiceover, translated_video}'

<?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']];

$script = $json($http->post('/v2/transcriptions', ['headers' => $h, 'json' => ['segments' => [[
    'speaker' => 'SPEAKER_00', 'start' => '00:00:00,500', 'end' => '00:00:04,800',
    'src' => ['text' => 'Welcome to the new dashboard.', 'lang' => 'en'],
    'dst' => ['text' => 'Bienvenido al nuevo panel.', 'lang' => 'es-mx'],
]]]]));

$p = $json($http->post('/v2/projects', ['headers' => $h, 'json' => [
    'video_id' => $videoId, 'dst_lang' => 'es-mx', 'transcript_id' => $script['id']]]));

while ($p['status'] !== 'merging_done') {
    sleep(10);
    $p = $json($http->get("/v2/projects/{$p['id']}", ['headers' => $h]));
}
echo $p['voiceover'];