Start Free with Transcribe Pro Vision MAX

You can get a Valossa API key immediately — no sales call, no waiting. Sign up for a Transcribe Pro Vision MAX free trial and you have everything you need to start calling the API and exploring the metadata output.

No credit card required to start

Create your free trial at valossa.com/transcribe-video-to-text-ai and get portal access within minutes.

---

What's Included in Transcribe Pro Vision MAX

Transcribe Pro Vision MAX gives you access to the broadest metadata output available as a self-serve subscription — covering nearly all detection types in the Valossa Core API.

✅ Included

Capability	Detection Types
Speech-to-text transcription	audio.speech, audio.speech_detailed
Speech subtitles (SRT/VTT)	Download via job_results?type=speech_to_text_srt
Speech keywords & named entities	audio.keyword.*
Visual objects & scenes	visual.context
Face detection & recognition	human.face, human.face_group
Celebrity identification	Via Valossa celebrities gallery (similar_to field)
Custom face gallery training	Full Face Training API access
Audio event detection	audio.context
Content moderation	content_compliance category across visual, audio, speech
Emotion & sentiment analysis	Face valence, named emotions, speech valence, audio.voice_emotion
IAB content categories	topic.iab, topic.general, topic.genre
OCR — visual text recognition	visual.text_region.*
Localized object bounding boxes	visual.object.localized, seconds_objects
Face bounding boxes	frames_faces metadata
Shot segmentation	segmentations
23+ languages for speech	See Language Support

❌ Not Included in Trial

Capability	What to do
Scene-level IAB ad context & Ad Score	topic.iab.section with Ad Score — contact sales for AdScout subscription
Automatic video clip generation	Autopreview — contact sales for Autopreview subscription

---

How to Get Started

Step 1: Sign Up for a Free Trial

Go to valossa.com/transcribe-video-to-text-ai and click "Start for Free".

Complete the registration form. You'll receive access to Valossa Portal immediately.

Step 2: Get Your API Key

1. Log in to Valossa Portal
2. Click your account name (top right) → My Account
3. Go to Subscriptions and API Keys
4. Copy your API key — it looks like: kkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkk

Keep it confidential. Never commit it to source control.

Step 3: Submit Your First Video

(Of course, alternatively you can send your video file by clicking in the graphical user interface of Valossa Portal and see the progress of the analysis job also there.)

Replace YOUR_API_KEY with your actual key and run:

curl -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "api_key": "YOUR_API_KEY",
    "media": {
      "video": {
        "url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/c/c0/Big_Buck_Bunny_4K.webm/Big_Buck_Bunny_4K.webm.480p.vp9.webm"
      }
    }
  }' \
  https://api-eu.valossa.com/core/1.0/new_job

You'll get back a job_id:

{ "job_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" }

Step 4: Poll for Completion

curl "https://api-eu.valossa.com/core/1.0/job_status?api_key=YOUR_API_KEY&job_id=YOUR_JOB_ID"

When status is "finished", move to Step 5.

Step 5: Download Your Results

curl "https://api-eu.valossa.com/core/1.0/job_results?api_key=YOUR_API_KEY&job_id=YOUR_JOB_ID" \
  -o my_video_metadata.json

You now have a JSON file with the full Valossa Core Metadata for your video — faces, speech, objects, topics, emotions, and more.

---

Next Steps

• Full Quickstart Guide — Complete walkthrough with Python and JavaScript examples
• Metadata Reference — Understand everything in your results JSON
• How-To Guides — Use cases: moderation, tagging, face recognition, subtitles
• API Reference — All 6 API endpoints documented

---

Frequently Asked Questions

Does the trial expire? The trial gives you short-term access to run analysis jobs and explore the Portal. For ongoing usage, upgrade to a paid plan directly from the Portal or contact sales for volume pricing.

Can I use the API during the trial? Yes — the API key you get from Portal works immediately for all included detection types.

What's the video file size limit? Up to 7 GB and up to 5 hours per video file. See Input Formats.

What languages are supported? 23 languages for speech-to-text, plus the experimental language autodetect feature that supports even more languages. See the Language Support table.

I need Ad Score / scene-level IAB categories. What do I do? These are available in the AdScout subscription. Contact Valossa sales for a quote.