Audio Understand
Endpoints
Audio Understand
Audio scene Q&A. Hears tone, music, SFX, language, speaker emotion. Custom Kyma endpoint, no OpenAI equivalent.
POST
Audio Understand
Synchronous endpoint for audio understanding beyond transcription. Upload a clip, ask a question — get back a natural-language answer that captures the parts a transcript loses: tone, mood, music style, ambient SFX, speaker emotion, language.
When to use this vs transcribe
A good rule of thumb: if the answer can be reconstructed from transcript text, use
transcribe. If it depends on how something sounds, use audio-understand.
Request
multipart/form-data upload.
file
required
Audio file. Supports
mp3, wav, m4a, ogg, webm, flac. Max 25 MB inline (~30 minutes of mono 16kHz mp3).string
required
Free-form text question about the audio. Be specific about what you want — “What is the mood?” is fine, but “Describe the music style, BPM, and any background SFX” gets more useful answers.
string
default:"audio-understand"
Either the alias
audio-understand (recommended) or a pinned SKU like gemini-3-flash-audio. See Audio models.number
Optional duration hint in seconds. When supplied, billing rounds up from this exact value. When omitted, Kyma estimates duration from file size (assumes 32 kbps mp3) which can over-estimate for high-bitrate inputs. Pass the real duration when you have it — that’s what
ffprobe gives you in one line.Response
200 OK with the answer text and a Kyma billing block.
string
The model’s answer to your question.
string
The Kyma model SKU that served the request.
string
Either
caller_hint (you passed duration_sec) or size_estimate (Kyma estimated from file bytes).number
Final cost charged for this request.
Pricing
Billed per minute, rounded up (a 30-second clip costs 1 minute = 0.039.
Errors
Examples
Mood and music brief for a video clip
Speaker emotion check
Pass exact duration for accurate billing
See also
- Audio Transcriptions - speech-to-text
- Audio models - SKUs behind the
audio-understandalias watch-cli- open-source CLI that pairs this endpoint withtranscribeto give agents full audio understanding from any social video URL