Generate music or podcast | EmpirioLabs AI Docs

Music / podcast / sound-effect generation. Distinct from /v1/audio/speech (TTS): this endpoint covers Stable Audio, GLM TTS, MOSS, and SoulX Podcast where the prompt-to-audio path is generative rather than spoken-word.

Long-running generations (> 60s) return 202 Accepted with a job_id and poll_url; poll /v1/jobs/{job_id} until complete.

Music / podcast / sound-effect generation. Distinct from `/v1/audio/speech` (TTS): this endpoint covers Stable Audio, GLM TTS, MOSS, and SoulX Podcast where the prompt-to-audio path is generative rather than spoken-word. Long-running generations (> 60s) return `202 Accepted` with a `job_id` and `poll_url`; poll `/v1/jobs/{job_id}` until complete.

Authentication

AuthorizationBearer

Pass your EmpirioLabs API key as a bearer token. The Anthropic-style x-api-key header is also accepted on every endpoint.

Request

This endpoint expects an object.

modelstringRequired

promptstringOptional

Natural-language description of the audio to generate.

inputstringOptional

Script / lyrics for podcast / multi-speaker models.

durationdoubleOptional

Output length in seconds.

stepsintegerOptional

Number of denoising steps. Higher = better quality but slower.

cfg_scaledoubleOptional

Prompt adherence. Higher = closer to prompt but less creative.

seedintegerOptional

Random seed for reproducibility.

output_formatenumOptional

Allowed values:

Response

Audio response (URL by default, or inline bytes).

datalist of objectsOptional

$	curl -X POST https://api.empiriolabs.ai/v1/audio/generations \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "stable-audio-2-5",
>	"prompt": "Lo-fi hip hop, mellow piano, gentle vinyl crackle, 90 BPM",
>	"duration": 60,
>	"steps": 8,
>	"cfg_scale": 1
>	}'

1	{
2	"data": [
3	{
4	"url": "https://cdn.empiriolabs.ai/audio/generated/lofi_hiphop_90bpm_001.mp3",
5	"duration": 60,
6	"format": "mp3"
7	}
8	]
9	}