Instrumental AI music for reels

A narration bed must leave room for speech. A dense melody or loud drums can distract even when the track sounds good on its own. Mureka v9 requires a lyrics field: for an instrumental attempt, use [Instrumental] and ask for no vocals in the prompt. Listen to the result rather than assuming the instruction was followed.

Prepare the shot

• Edit the narrated reel first and mark where music can come forward.
• Describe two or three instruments and the rhythm without requesting a specific artist imitation.
• Use [Instrumental] in lyrics and request no singing or spoken fragments in the prompt.
• Listen to the complete output, including later sections where vocals might appear.
• Choose a passage that fits the edit and cut at a musical phrase boundary.
• Lower the music under speech and check the exported reel on a phone speaker.

Review before publication

• No vocals appear in the chosen passage.
• Narration is intelligible on a phone.
• The ending follows a musical phrase.

API input example

The JSON below is the request body for POST /v1/generate. Use your own accessible image URL where a reference is required.

{
  "model": "mureka-v9",
  "input": {
    "prompt": "Calm instrumental lo-fi, soft piano and gentle percussion, room for narration, no vocals",
    "lyrics": "[Instrumental]"
  }
}

Model and cost

Use Mureka V9. Its current unit price is $0.124 per song. Check the pricing page and calculator for your settings. Credits never expire, there is no subscription and failed generations are free. A successful output is billable even if you choose not to publish it.

FAQ

Must the generated track exactly match the reel length?

No. Select a passage and trim it in your editor. Do not assume an exact duration unless the model exposes that control.

Can I check the request before a paid run?

Yes. Check the model schema and the cost shown in Studio. Local demo API tests validate request handling but do not prove the visual or audio quality of the real model.

Where are the supported parameters?

Model details and the generation API guide list the supported inputs. Preview mode does not provide a real generated result.