Seed Audio API

At a glance

The Seed Audio API runs Seed Audio through Mage at POST https://api.mage.space/v1/seed_audio/generate. A request at the default settings costs 19 Gems (about $0.019), with no subscription. Seed Audio takes saved audio references by @handle in the prompt.

• Audio

  Output

• 1

  Variant

• 19

  Gems per clip, default

• $0.019

  About, in USD

Overview

What the Seed Audio API does

Speech, dialogue, music, and sound effects from a single prompt, as an MP3 of exactly the length you ask, 5 seconds to 2 minutes. Match a voice from up to 3 audio clips.

Voices, dialogue, music, and sound effects from one prompt, as an MP3 of exactly the requested duration.

It accepts image as inputs.

Quick start

Call the Seed Audio API

Set MAGE_API_KEY, submit to /seed_audio/generate, and poll status_url until the request completes.

STATUS_URL=$(curl --request POST 'https://api.mage.space/v1/seed_audio/generate' \
  --header "Authorization: Bearer $MAGE_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "prompt": "A calm narrator reading a short weather report",
  "duration": "5",
  "model_id": "seed-audio-1.0"
}' | jq -r '.status_url')

# Repeat until status is "completed"; result.url is the file
curl "$STATUS_URL" --header "Authorization: Bearer $MAGE_API_KEY"

import os, time, requests

headers = {"Authorization": f"Bearer {os.environ['MAGE_API_KEY']}"}
request = requests.post(
    "https://api.mage.space/v1/seed_audio/generate",
    headers=headers,
    json={
      "prompt": "A calm narrator reading a short weather report",
      "duration": "5",
      "model_id": "seed-audio-1.0"
    },
).json()

while request["status"] in ("queued", "in_progress"):
    time.sleep(3)
    request = requests.get(request["status_url"], headers=headers).json()

print(request["status"], request["result"] and request["result"]["url"])

const headers = {
  Authorization: `Bearer ${process.env.MAGE_API_KEY}`,
  'Content-Type': 'application/json',
};
let request = await fetch('https://api.mage.space/v1/seed_audio/generate', {
  method: 'POST',
  headers,
  body: JSON.stringify({
    "prompt": "A calm narrator reading a short weather report",
    "duration": "5",
    "model_id": "seed-audio-1.0"
  }),
}).then((response) => response.json());

while (['queued', 'in_progress'].includes(request.status)) {
  await new Promise((resolve) => setTimeout(resolve, 3000));
  request = await fetch(request.status_url, { headers }).then((r) => r.json());
}

console.log(request.status, request.result?.url);

Models

Seed Audio model_id values

Send model_id to pick a variant. A request without one runs the default.

Options

Seed Audio parameters

Allowed values across all variants; a variant may offer fewer. The docs list the options per variant.

Inputs

Media inputs Seed Audio accepts

Send each as an https URL, a data URL, or an upload of up to 100 MB.

Rules

What the Seed Audio API enforces

• An image reference cannot be combined with audio references: send one kind or the other.
• The prompt is at most 2986 characters.
• `sample_rate` is one of 8000, 16000, 24000, 32000, 44100, 48000.
• `speech_rate` is a whole number from -50 to 100.
• `loudness_rate` is a whole number from -50 to 100.
• `pitch_rate` is a whole number from -12 to 12.

More audio models

Other audio generation APIs on Mage

FAQ

Frequently asked questions

Start building with Mage

One account, one Gems balance, every model. Pay only for what you generate.

Related

• AI audio generation API
• Seed Audio API reference
• Seed Audio playground
• All API models
• Mage MCP server