Audio

Flenly supports two types of audio for your generated videos: native AI-generated audio and uploaded audio files.

Native Audio

Some models can generate audio that matches the video content automatically. The AI creates sound effects, ambient noise, and environmental audio based on your scene prompt.

Models with native audio:

• Veo 3.1 / Veo 3.1 Fast
• Kling v2.6
• Seedance 1.5 Pro
• Sora 2
• LTX-2 Fast / LTX-2 Pro

Enabling native audio increases the coin cost per second. For example, Veo 3.1 costs 25 coins/s without audio and 50 coins/s with audio.

You can toggle native audio on or off for each render.

Audio File Upload

For models that don't support native audio (or when you want specific audio), you can upload your own audio file:

Models with audio file support:

• Wan 2.6 I2V
• Wan 2.6 T2V

Upload an MP3 or WAV file, and the generated video will sync with your audio. This is useful for:

• Music videos
• Narrated scenes
• Scenes with specific sound effects
• Dialogue-driven content

Upload audio files through the Asset Library first, then select them when configuring your render.

No Audio

Some models don't support audio at all:

• Hailuo 2.3 / Hailuo 2.3 Fast
• PixVerse v5

Videos from these models will be silent. You can add audio later in a separate video editing tool if needed.