Image and audio models from fal now available on DigitalOcean

We’re excited to announce the launch of four multimodal AI models from fal , now through Serverless Inference. These models allow you to generate images and audio directly via API, without worrying about infrastructure, scaling, or vendor management. With this release, building AI-powered applications that include visual and audio content is easier than ever.

Explore the new models

The fal models, now in public preview, cover a variety of modalities, enabling you to experiment, prototype, and deploy multimodal AI features quickly:

Image generation:

• Stable Diffusion XL fast (fal-ai/fast-sdxl) – High-resolution image generation

• FLUX.1 (schnell) (fal-ai/flux/schnell) – Fast image generation for quick prototyping

Audio generation:

• Stable Audio (fal-ai/stable-audio-25/text-to-audio) – Convert text into natural-sounding audio

• ElevenLabs TTS Multilingual v2 9 (fal-ai/elevenlabs/tts/multilingual-v2) – Multilingual text-to-speech

Try it out

You can start using these models through the Serverless Inference API (https://inference.do-ai.run) after opting in to the public preview in the DigitalOcean console. Here’s a quick look at how to interact with them:

Example: Generate an Image

export MODEL_ACCESS_KEY="YOUR_KEY"
curl -sS -X POST 'https://inference.do-ai.run/v1/async-invoke' \
  -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "fal-ai/flux/schnell",
    "input": { "prompt": "A high-quality photo of a futuristic city at sunset" }
  }'

Example: Generate an Image with Customized Parameters

export MODEL_ACCESS_KEY="YOUR_KEY"
curl -sS -X POST 'https://inference.do-ai.run/v1/async-invoke' \
  -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "fal-ai/fast-sdxl",
    "input": {
      "prompt": "A high-quality photo of a futuristic city at sunset",
      "output_format": "landscape_4_3",
      "num_inference_steps": 4,
      "guidance_scale": 3.5,
      "num_images": 1,
      "enable_safety_checker": true
    },
    "tags": [
      { "key": "type", "value": "test" }
    ]
  }'

Example: Generate Sound

export MODEL_ACCESS_KEY="YOUR_KEY"
curl -sS -X POST 'https://inference.do-ai.run/v1/async-invoke' \
  -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "fal-ai/stable-audio-25/text-to-audio",
    "input": {
      "prompt": "Futuristic epic song",
      "seconds_total": 60
    },
    "tags": [
      { "key": "type", "value": "test" }
    ]
  }'

Example: Text to Speech (TTS)

export MODEL_ACCESS_KEY="YOUR_KEY"
curl -sS -X POST 'https://inference.do-ai.run/v1/async-invoke' \
  -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "fal-ai/elevenlabs/tts/multilingual-v2",
    "input": {
      "text": "Hello, this is a text to speech example using Digital Ocean multilingual voice."
    },
    "tags": [
      { "key": "type", "value": "test" }
    ]
  }'

Check the request status

These requests start the job and return a request_id, which you can use to check when your image is ready. Because Serverless Inference uses an asynchronous API, you’ll need to poll the request until it completes.

The /status endpoint is lightweight, so you can query it frequently to check progress. Once the job shows COMPLETE, use the /async-invoke/{request_id} endpoint to fetch the full generated result.

curl -sS -X GET "https://inference.do-ai.run/v1/async-invoke/{request_id}/status" \
  -H "Authorization: Bearer $MODEL_ACCESS_KEY"

Keep polling this endpoint until the response shows:

{ "status": "COMPLETE" }

Retrieve the final result

Once the job is complete, you can get the full response (which includes your generated image) using:

curl -sS -X GET "https://inference.do-ai.run/v1/async-invoke/{request_id}" \
  -H "Authorization: Bearer $MODEL_ACCESS_KEY"

The returned JSON includes a URL to the generated audio file, which you can download or play directly in your browser or app.

curl -O "{url}"

Bring your ideas to life with fal on DigitalOcean

With these four new multimodal models in public preview, you can now build richer AI-powered experiences, generating images and audio without managing infrastructure.

Get started today by exploring the Serverless Inference API and integrating these powerful fal models into your applications.