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).
|
{
"type": "object",
"title": "Input",
"required": [
"prompt"
],
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"default": -1,
"x-order": 3,
"description": "Random seed. -1 = random."
},
"steps": {
"enum": [
2,
3,
4,
5,
6,
8
],
"type": "integer",
"title": "steps",
"description": "Denoising steps from the distilled schedule.",
"default": 3,
"x-order": 4
},
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 0,
"description": "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."
},
"vocoder": {
"enum": [
"fp32",
"bf16",
"nobwe"
],
"type": "string",
"title": "vocoder",
"description": "TEST: fp32 = stock 48 kHz (v4), bf16 = bf16 vocoder convs, nobwe = skip the 48 kHz bandwidth extension.",
"default": "fp32",
"x-order": 6
},
"duration": {
"type": "number",
"title": "Duration",
"default": 0,
"maximum": 20,
"minimum": 0,
"x-order": 2,
"description": "Seconds of audio per line, rounded up to the next 0.5 s. 0 = let the model pick."
},
"ancestral": {
"type": "boolean",
"title": "Ancestral",
"default": true,
"x-order": 5,
"description": "Ancestral sampler (what LTX-2.5 uses)."
},
"cache_text": {
"type": "boolean",
"title": "Cache Text",
"default": false,
"x-order": 7,
"description": "TEST: reuse text-encoder output for prompts seen before on this replica."
},
"more_prompts": {
"type": "string",
"title": "More Prompts",
"default": "",
"x-order": 1,
"description": "TEST: JSON list of more prompts, generated in the SAME batched call (one output each)."
},
"output_format": {
"enum": [
"mp3",
"wav"
],
"type": "string",
"title": "output_format",
"description": "Audio format (mp3 = mono 96 kbps, wav = mono 16-bit).",
"default": "mp3",
"x-order": 8
}
}
}
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"
}