← All models
Studio-quality speech from noisy recordings
Details
- Accepts
- text
Pricing
- Price
- 1.56 cr / minute
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| strength | number | How much of the original is allowed to remain under speech: the suppression floor is 1 - strength (the default 0.874 is the validated -18 dB). Lower keeps more room tone behind the voice; silence between words is always fully cleaned. |
| audio_urlrequired | string | The recording to clean. Any audio or video ffmpeg can decode (wav, mp3, m4a, aac, ogg, mp4, mov, webm, ...); a video's audio track is used and multi-channel input is mixed down to mono. Up to 30 minutes and 512 MB. A public URL or a data URI. |
| target_lufs | — | Integrated loudness of the output (ITU-R BS.1770). The default -19 LUFS is the level the VEED editor delivers; true peak is capped at -1.1 dBTP. Pass null through the API to skip loudness normalization and keep the input level. |
| output_format | stringenum: flac, wav | Container for the 48 kHz mono 16-bit output. FLAC is lossless at about half the size of WAV. |
Output
| Field | Type | Description |
|---|---|---|
| audio | — | The denoised recording: 48 kHz mono 16-bit, same duration as the input, loudness-normalized. |
| audio_duration | number | Input duration in seconds. Billing: whole seconds rounded up to full minutes, minimum 1 unit. |