Speech, music, and sound generation models on a unified API.
Audio generation models on EmpirioLabs cover text-to-speech, music, and sound effects, with options like multiple speakers or voice cloning depending on the model. You send your text or prompt and retrieve audio, billed per generation or per minute.
Each model's lowest listed rate, read live from its rate card, cheapest first. A model's page lists every rate and option.
Priced by characters of text
| Model | Lowest rate | Applies to |
|---|---|---|
| TTS 2 Flash Inworld | $15.00$10.50 per 1M characters | Synthesis |
| StepAudio 3 Gen StepFun | $0.14 per 10,000 characters | Generation |
| StepAudio 3 TTS StepFun | $0.14 per 10,000 characters | Synthesis |
| Qwen Audio 3.0 TTS Alibaba Cloud | $0.15 per 10,000 characters | Flash synthesis |
| SoulX Podcast Soul AI Lab | $0.015 per 1k characters, minimum 700 characters per request | Base |
| TTS 1.5 Mini Inworld | $25.00$17.50 per 1M characters | Synthesis |
| TTS 2 Inworld | $25.00$22.00 per 1M characters | Synthesis |
| TTS 1.5 Max Inworld | $35.00$29.75 per 1M characters | Synthesis |
| Model | Lowest rate | Applies to |
|---|---|---|
| Qwen Audio 3.1 TTS Plus Alibaba Cloud | $0.60 per 10,000 characters | Synthesis |
| StepAudio 2.5 TTS StepFun | $0.85 per 10,000 characters | Synthesis |
| GLM TTS Z.ai | $0.20 per 1k characters, minimum 50 characters per request | Fast (INT8) |
Priced per second
| Model | Lowest rate | Applies to |
|---|---|---|
| ACE-Step 1.5 XL ACE-Step | $0.0003$0.00025 per generated second | Music generation |
| StepAudio 3 Music StepFun | $0.000667 per generated second | Text to music |
| Sonilo Audio Ducking Sonilo | $0.0012 per generated second | Audio ducking |
| MiniMax Music 3 MiniMax | $0.002$0.0018 per generated second | Music generation |
| Sonilo Sound Effects 1.0 Sonilo | $0.0036 per generated second | Text to sound effect |
| Sonilo v1.1 Sonilo | $0.0045 per generated second | Text to music |
Models billed in other units are not ranked here. Each model's page has its full rate card.
ACE-Step 1.5 XL runs through POST /v1/audio/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Swap the model id for any model above. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/audio/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ace-step-1-5-xl",
"prompt": "Describe what you want ACE-Step 1.5 XL to generate."
}'EmpirioLabs lists 39 Audio Generation model APIs, including ACE-Step 1.5 XL, TTS 2, TTS 1.5 Mini. Each model has its own dedicated API page with live pricing, parameters, and a quickstart.
Pay as you go, or choose a plan with weekly allowances. The exact rate card lives on each model's page and always matches what the API charges.
TTS 2 Flash lists the lowest rate per character of the 11 Audio Generation models priced that way, followed by StepAudio 3 Gen, StepAudio 3 TTS. The price table on this page shows each model's lowest rate and what it applies to.
No. Every model here runs in the EmpirioLabs playground, a friendly in-browser interface where you can set the options and see results without writing any code. When you are ready to automate, the same model is available through the API.
Check out our pricing or reach out if you want your own model deployed on our stack.