Video 1.0 generate_audio: why the docs say to omit it
Sume's Auto family always generates audio for Video 1.0 requests, so the docs tell you to omit generate_audio. What the field does and where audio is optional.
On Video 1.0 the current Auto family always generates audio, so the docs say to omit generate_audio. The field is still a boolean in the legacy shape, but there is nothing to switch off.
What does the Video 1.0 field table say?
generate_audio is listed as an optional boolean: the current Auto family always generates audio; omit this field. bitrate_mode is a related legacy field that Auto rejects.
Where is audio a choice?
On /v1/videos, generate_audio defaults to the model's audio capability, and each catalog model reports a generate_audio flag. gemini-omni-flash-1.1 keeps native audio always on and rejects generate_audio: false.
| Route or model | Audio |
|---|---|
| POST /v1/video-1.0/generate | Always generated; omit the field |
| POST /v1/videos | Defaults to the model's capability |
| gemini-omni-flash-1.1 | Always on; false is rejected |
| minimax-h3-max | Native stereo audio |
How do I handle a silent deliverable?
Video 1.0 cannot be told to skip audio, so remove or mute it downstream. The Timeline docs cover a silence audio mode for joined edits.
Which route should new work use?
Use /v1/videos, which lists per-model audio flags. See the video generation docs.
What does the request table say about `mode`?
Video 1.0 accepts mode values async, sync, subscribe and webhook. wait_timeout_seconds is 0 to 30 for sync and subscribe, and webhook_url must be a public HTTPS callback for webhook mode.
Sources
Related posts
More in Developers
- Video 1.0 metadata field: stored on the job, not sent upstream
The metadata object on a Video 1.0 request is stored on the job as caller metadata and is not sent to the provider. Use it to tag jobs; the limits it has.
- Video 1.0 reference_audio_urls: why audio alone is rejected
In Video 1.0, reference_audio_urls (1 to 3 URLs) requires at least one reference image or video. Field limits for images, videos and audio references.
- routing_preset kling or grok on Video 1.0: accepted, then ignored
Video 1.0 still accepts the retired routing_preset values cost, speed, quality, grok and kling, but all of them run through Auto. How to pick a family instead.
- Video analyses API returns 410 video_analysis_retired: fix
POST /v1/video-analyses answers 410 video_analysis_retired in Sume's dest environment. Stored rows stay readable; new clip inspection uses video inspect.
Written by Sume