usamaehsan/ltx-voice
LTX-2.5 voice only: expressive text-to-speech from the audio half of LTX-2.5 (no video). Designed voices from a text prompt, no voice cloning.
Public
1.7K
runs
Run usamaehsan/ltx-voice 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.
|
|
| duration |
number
|
0
Max: 20 |
Seconds of audio, rounded up to the next 0.5 s. 0 = let the model pick from the prompt.
|
| seed |
integer
|
-1
|
Random seed. -1 = random.
|
| steps |
None
|
8
|
Denoising steps from the distilled schedule (8 = full quality).
|
| refine |
boolean
|
False
|
Extra 3-step refine pass (like stage 2 of the video model).
|
| ancestral |
boolean
|
True
|
Ancestral sampler (what LTX-2.5 uses).
|
| output_format |
None
|
mp3
|
Audio format (mp3 = mono 96 kbps, wav = stereo 16-bit).
|
| trim_text |
boolean
|
True
|
Run the text encoder on the real prompt tokens only (fast).
|
| profile |
boolean
|
False
|
Speed-test debug: return the torch.compile mega-cache of this replica (a .bin) instead of audio.
|
{
"type": "object",
"title": "Input",
"required": [
"prompt"
],
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"default": -1,
"x-order": 2,
"description": "Random seed. -1 = random."
},
"steps": {
"enum": [
3,
4,
5,
6,
8
],
"type": "integer",
"title": "steps",
"description": "Denoising steps from the distilled schedule (8 = full quality).",
"default": 8,
"x-order": 3
},
"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."
},
"refine": {
"type": "boolean",
"title": "Refine",
"default": false,
"x-order": 4,
"description": "Extra 3-step refine pass (like stage 2 of the video model)."
},
"profile": {
"type": "boolean",
"title": "Profile",
"default": false,
"x-order": 8,
"description": "Speed-test debug: return the torch.compile mega-cache of this replica (a .bin) instead of audio."
},
"duration": {
"type": "number",
"title": "Duration",
"default": 0,
"maximum": 20,
"minimum": 0,
"x-order": 1,
"description": "Seconds of audio, rounded up to the next 0.5 s. 0 = let the model pick from the prompt."
},
"ancestral": {
"type": "boolean",
"title": "Ancestral",
"default": true,
"x-order": 5,
"description": "Ancestral sampler (what LTX-2.5 uses)."
},
"trim_text": {
"type": "boolean",
"title": "Trim Text",
"default": true,
"x-order": 7,
"description": "Run the text encoder on the real prompt tokens only (fast)."
},
"output_format": {
"enum": [
"mp3",
"wav"
],
"type": "string",
"title": "output_format",
"description": "Audio format (mp3 = mono 96 kbps, wav = stereo 16-bit).",
"default": "mp3",
"x-order": 6
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "string",
"title": "Output",
"format": "uri"
}