Skip to content

docs: Kyma endpoint table and Runs on Kyma line #21

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sonpiaz merged 1 commit into from
Sep 13, 2026
Merged

docs: Kyma endpoint table and Runs on Kyma line #21

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,11 +165,20 @@ sudo apt install yt-dlp ffmpeg jq python3 curl
export KYMA_API_KEY=kyma-xxxxxxxx
```

Get a Kyma key at [kymaapi.com](https://kymaapi.com/?src=skill:watch) — 60 seconds, no card.
Get a Kyma key at [kymaapi.com](https://kymaapi.com?utm_source=watch-cli). About 60 seconds, no card.

Prefer bring-your-own-keys? Comment in `GROQ_API_KEY` and `GOOGLE_AI_KEY`
in `.env.example` and watch-cli falls back to direct provider calls.

Runs on [Kyma API](https://kymaapi.com?utm_source=watch-cli): one key covers speech-to-text and audio scene Q&A for every `watch` / `transcribe` / `audio-q` run.

Default Kyma calls (scripts send capability aliases; Kyma resolves them to the models below):

| Role | Model | Kyma endpoint | Best for |
|------|-------|---------------|----------|
| Transcribe (alias `transcribe`) | [`whisper-v3-turbo`](https://kymaapi.com/models/whisper-v3-turbo?utm_source=watch-cli) | `POST https://kymaapi.com/v1/audio/transcriptions` | Speech-to-text for any social video |
| Audio Q&A (alias `audio-understand`) | [`gemini-3-flash-audio`](https://kymaapi.com/models/gemini-3-flash-audio?utm_source=watch-cli) | `POST https://kymaapi.com/v1/audio/understand` | Tone, music, SFX, language, emotion |

---

## Why Kyma
Expand Down
Loading