Extract word-for-word transcripts from YouTube, TikTok, Twitter, Twitch & more. AI-powered with noise reduction, 100+ language translation, and 95% accuracy.
https://api.transcripthq.ioPlatforms & Endpoints
Get your first transcript in under 5 minutes
Keep your API key secure. Never expose it in client-side code or public repositories.
Create a transcript job by sending a POST request:
curl -X POST https://api.transcripthq.io/v1/transcripts \
-H "Content-Type: application/json" \
-H "X-API-Key: YOUR_API_KEY" \
-d '{
"service_type": "youtube",
"videos": ["dQw4w9WgXcQ"]
}'
Response:
{
"job_id": "675f1a2b3c4d5e6f7a8b9c0d",
"status": "processing",
"videos_count": 1,
"credits_charged": 4,
"poll_url": "/v1/transcripts/675f1a2b3c4d5e6f7a8b9c0d"
}
Jobs process asynchronously. Poll every 2-3 seconds until status is "completed":
curl https://api.transcripthq.io/v1/transcripts/675f1a2b3c4d5e6f7a8b9c0d \
-H "X-API-Key: YOUR_API_KEY"
Completed Response:
{
"job_id": "675f1a2b3c4d5e6f7a8b9c0d",
"status": "completed",
"summary": { "total": 1, "done": 1, "failed": 0 },
"videos": [{
"video_id": "dQw4w9WgXcQ",
"status": "done",
"title": "Rick Astley - Never Gonna Give You Up",
"duration_seconds": 213.5,
"transcript": "We're no strangers to love...",
"segments": [
{ "text": "We're no strangers to love", "start": 0.5, "duration": 2.1 }
],
"language": "en",
"is_native": true,
"is_generated": false
}],
"credits_used": 4
}
"noise_reduction": true for cleaner audio"target_language": "en" to translate"word_timestamps": trueAll API requests require an API key in the header:
X-API-Key: YOUR_API_KEY
X-API-KeyThese parameters work with all service_type values (YouTube, Twitter, Twitch, etc.):
service_type"youtube" (default), "twitter", "twitch", "vimeo", "tiktok", "dailymotion", "bilibili"
videos*Array of video IDs or URLs
max_videosLimit videos from playlist/channel (default: 100)
word_timestampsEnable word-level timestamps (Pro feature)
source_languageISO 639-1 language hint for Whisper (e.g., "zh", "ta", "hi"). Auto-detects if omitted. Improves accuracy and speed for non-English.
target_languageTranslate transcript to this language (e.g., "en", "es", "fr")
noise_reductionApply audio cleaning before transcription (default: false)
native_onlySkip Whisper fallback, only use native captions (default: false). Videos without captions will fail.
skip_metadataSkip upfront metadata scan for faster job creation (default: false)
| Plan | Rate Limit | Concurrent Jobs |
|---|---|---|
| Free | 30/min | 1 |
| Starter | 100/min | 2 |
| Pro | 300/min | 2 |
| Business | 500/min | 5 |
| Enterprise | 500/min | Unlimited |