Build with the
Streamdiver Media API

Automated media processing, transcription, and publishing for audio, video, images, and documents – 100% GDPR compliant, hosted in Europe.

# Agentic Workflow: Council Meeting → Protocol

POST /api/v2/livestream/start
→ 200 OK { "streamId": "sess-2026-01-28" }

⏳ Recording... 1h 23m
⏳ Processing transcript...
✓ Speakers identified (3)
✓ Topics extracted (12)

POST /api/v2/workflows/protocol
→ Generating protocol draft...

{
  "workflow": "council-meeting-protocol",
  "status": "completed",
  "duration": "3m 42s",
  "results": {
    "transcript": {
      "status": "✓ complete",
      "speakers": [
        "Dr. Weber",
        "Mayor Schmidt",
        "Councillor Müller"
      ]
    },
    "protocol": {
      "status": "✓ draft ready",
      "sections": 12,
      "decisions": 5
    },
    "outputs": [
      "protocol_draft.pdf",
      "citizen_summary.html",
      "press_release.docx"
    ]
  }
}
ISO 27001 Compliant
GDPR Compliant
Developed in Europe
100+ Organizations

Built for Developers

Publishing suite with live configuration and a complete REST API.

Player

Embed videos and audio cookie-free with custom branding

Channel Slider

Carousel display for video, audio, images, and documents

Media Library

Fully searchable embedded media library for video, audio, and docs

OpenAPI 3.0Interactive documentation and client generation
WebhooksReal-time events
OAuth 2.0Secure authentication
S3 UploadReliable data transfer

Digital SovereigntyYour Data Stays in Europe

No US cloud services (no Cloud Act)
ISO 27001 certified data centers in AT/DE
Own AI models – no data to OpenAI/Anthropic
Geo-redundant infrastructure in DACH region
Cookie-free widgets – no consent required

One API for the entire media lifecycle

From ingest to publication – one continuous workflow through a unified REST API.

01

Ingest

Upload, live stream, and import

  • RTMP live stream
  • S3-compatible upload
  • Feed import (RSS/MRSS)
02

Transcode

Conversion

  • Adaptive bitrate (HLS)
  • Thumbnail generation
  • Format optimization
03

AI processing

Extract metadata

  • Transcription & speaker ID
  • OCR & entity extraction
  • Semantic indexing
04

Enrich

Optimize content

  • Auto subtitles & transcript
  • Chapters & descriptions
  • SEO metadata
05

Publish

Widgets & portals

  • Customizable video libraries
  • Search & tag filtering
  • Content recommendations

AI pipeline – From upload to insight

Automatic metadata extraction in three processing stages.

Stage I

Extraction

Derive structured data from raw media

  • Transcription (STT/ASR)
  • Speaker recognition
  • Keyframe extraction
  • Text recognition (OCR)
Stage II

Enrichment

Analysis and metadata enrichment

  • Entity extraction
  • Chapter generation
  • Summaries
  • Text embeddings
Stage III

Search & retrieval

Make content searchable and AI-ready

  • Semantic search
  • Question answering (RAG)
  • Full-text search

Ready to test the API?

Request a trial account and explore the interactive documentation.

Request Trial

Frequently Asked Questions

Answers to the most important questions.

Contact us for a trial account. You'll receive OAuth 2.0 credentials and access to a dedicated test environment with full API functionality. You can already explore the interactive API reference.
Streamdiver offers two integration paths: The Publishing Suite (player, channel slider, media library) for fast, cookie-free embedding via embed code without a cookie banner, and the full REST API (OpenAPI 3.0) for deep system integration. Webhooks enable event-driven workflows. Uploads are S3-compatible.
All data is processed exclusively in ISO 27001 certified data centers in Austria and Germany. There is no data transfer to US cloud providers. AI models run self-hosted in our European infrastructure – with no data sharing to third parties.
The API provides automatic transcription in 50+ languages, speaker recognition, chapter generation, summaries, entity extraction, semantic search, and RAG-based Q&A. All AI results are available as structured JSON via the REST API.
Yes, GDPR compliant by design. No US cloud services (no Cloud Act), self-hosted AI models without data sharing, all data centers in the EU. The Publishing Suite sets no cookies and requires no cookie banner – unlike YouTube embeds. We provide data processing agreements (DPAs) for personal data processing.