Audio

Audio on Kyma splits four ways:

Transcription — what was said. OpenAI Whisper API compatible. POST /v1/audio/transcriptions
Audio understanding: retired on 8 October 2026 with its only model, gemini-3-flash-audio. POST /v1/audio/understand now answers 404 model_not_found.
Speech — text to voice, voice cloning, voice design, music. Browse them by creator in this section.
Realtime: streaming voice and live translation are paused as of 12 September 2026, so no realtime model is being served.

This page covers transcription: a synchronous endpoint, billed per minute of processed audio. It is sync (no polling), uses multipart/form-data upload, and accept mp3 / wav / m4a / ogg / webm / flac up to 25 MB (~30 min of mono 16kHz mp3).

Pick a model

Model	Endpoint	Best for	Cost / min	Min billable
`whisper-v3-turbo`	`/v1/audio/transcriptions`	Transcripts, captions, voice agents	$0.0009	1 min
`gpt-transcribe`	`/v1/audio/transcriptions`	Noisy, conversational and code-switching audio (no timestamps)	$0.006075	1 min
`gemini-3.5-transcribe`	`/v1/audio/transcriptions`	Google file STT (pin the SKU; `transcribe` alias unchanged)	$0.00675	1 min

Billed in 1-minute increments, rounded up. A 1-hour file with whisper-v3-turbo: $0.054.

Aliases

Use these in the model field instead of pinning a specific SKU. Aliases auto-track the current best model — when a faster Whisper or a stronger Gemini lands, you don’t change your code.

Alias	Resolves to
`transcribe`	`whisper-v3-turbo`

whisper-v3-turbo

Speech-to-text. 228x realtime inference. Returns transcripts with per-segment timestamps and detected language. OpenAI Whisper API compatible.

curl -X POST https://kymaapi.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -F "file=@meeting.mp3" \
  -F "model=transcribe"

Cost: $0.0009 / min
Best for: meeting notes, voice agent input, podcast captions
Output: text + segments with timestamps

Use them together — the decomposition trick

A video is just frames + audio. You almost never need a multimodal LLM on the full video — each piece has a fast, near-free tool:

URL ──▶ yt-dlp ──▶ video.mp4 ──┬──▶ ffmpeg ──▶ frames/*.jpg
                                │
                                └──▶ ffmpeg ──▶ audio.mp3 ───▶ /v1/audio/transcriptions
                                                                  (the words)

watch-cli is an open-source orchestrator built on exactly this pattern — install it, point at any social video URL, and your agent gets back frames + transcript.

Approach	Cost / 1-hour video	Time
Multimodal LLM on full video	~$5	30-60s
Decompose with Kyma audio	~$0.05	~10-15s

The savings compound when an agent watches dozens of videos in a session.

Models

Pick a model

Aliases

whisper-v3-turbo

Use them together — the decomposition trick

See also

​Pick a model

​Aliases

​whisper-v3-turbo

​Use them together — the decomposition trick

​See also

Pick a model

Aliases

whisper-v3-turbo

Use them together — the decomposition trick

See also