usamaehsan/ltx-voice-cheap-test

TEST ONLY: cost experiments for the LTX-2.5 voice model (batching, vocoder precision). Not for any site.

Public
15 runs

Run usamaehsan/ltx-voice-cheap-test with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
prompt
string
Describe the speaker, the emotion and the room, and put the exact words in quotes, e.g. A tired old man says softly: "I waited all night for you." Quiet room, no music.
more_prompts
string
TEST: JSON list of more prompts, generated in the SAME batched call (one output each).
duration
number
0

Max: 20

Seconds of audio per line, rounded up to the next 0.5 s. 0 = let the model pick.
seed
integer
-1
Random seed. -1 = random.
steps
None
3
Denoising steps from the distilled schedule.
ancestral
boolean
True
Ancestral sampler (what LTX-2.5 uses).
vocoder
None
fp32
TEST: fp32 = stock 48 kHz (v4), bf16 = bf16 vocoder convs, nobwe = skip the 48 kHz bandwidth extension.
cache_text
boolean
False
TEST: reuse text-encoder output for prompts seen before on this replica.
output_format
None
mp3
Audio format (mp3 = mono 96 kbps, wav = mono 16-bit).

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "array",
  "items": {
    "type": "string",
    "format": "uri"
  },
  "title": "Output"
}