usamaehsan/supertonic-3-tts
Fast multilingual text-to-speech (31 languages, 10 preset voices, no cloning). Supertonic 3 weights, OpenRAIL-M: outputs must be disclosed as machine generated; see the README for the use restrictions.
Run usamaehsan/supertonic-3-tts 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 |
|---|---|---|---|
| text |
string
|
Once upon a time there was a small turtle who lived beside a quiet river.
|
Text to speak. Long text is split into sentences automatically.
|
| language |
None
|
en
|
Language of the text. Use 'na' to let the model decide.
|
| voice |
None
|
F1
|
Preset voice style. F = female, M = male.
|
| steps |
integer
|
8
Min: 1.0 Max: 16.0 |
Denoising steps. Higher is cleaner and slower.
|
| speed |
number
|
1.05
Min: 0.5 Max: 2.0 |
Speaking speed. Higher is faster.
|
| silence |
number
|
0.3
Max: 2.0 |
Seconds of silence inserted between sentences.
|
| batch_sentences |
boolean
|
True
|
Synthesize all sentences in one batched pass. Much faster on GPU.
|
| output_format |
None
|
mp3
|
Audio format of the returned file.
|
| mp3_bitrate |
None
|
96k
|
Bitrate used when output_format is mp3.
|
| seed |
integer
|
Random seed. Leave blank for a random one.
|
{
"type": "object",
"title": "Input",
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 9,
"nullable": true,
"description": "Random seed. Leave blank for a random one."
},
"text": {
"type": "string",
"title": "Text",
"default": "Once upon a time there was a small turtle who lived beside a quiet river.",
"x-order": 0,
"description": "Text to speak. Long text is split into sentences automatically."
},
"speed": {
"type": "number",
"title": "Speed",
"default": 1.05,
"maximum": 2.0,
"minimum": 0.5,
"x-order": 4,
"description": "Speaking speed. Higher is faster."
},
"steps": {
"type": "integer",
"title": "Steps",
"default": 8,
"maximum": 16.0,
"minimum": 1.0,
"x-order": 3,
"description": "Denoising steps. Higher is cleaner and slower."
},
"voice": {
"enum": [
"F1",
"F2",
"F3",
"F4",
"F5",
"M1",
"M2",
"M3",
"M4",
"M5"
],
"type": "string",
"title": "voice",
"description": "Preset voice style. F = female, M = male.",
"default": "F1",
"x-order": 2
},
"silence": {
"type": "number",
"title": "Silence",
"default": 0.3,
"maximum": 2.0,
"minimum": 0.0,
"x-order": 5,
"description": "Seconds of silence inserted between sentences."
},
"language": {
"enum": [
"en",
"ko",
"ja",
"ar",
"bg",
"cs",
"da",
"de",
"el",
"es",
"et",
"fi",
"fr",
"hi",
"hr",
"hu",
"id",
"it",
"lt",
"lv",
"nl",
"pl",
"pt",
"ro",
"ru",
"sk",
"sl",
"sv",
"tr",
"uk",
"vi",
"na"
],
"type": "string",
"title": "language",
"description": "Language of the text. Use 'na' to let the model decide.",
"default": "en",
"x-order": 1
},
"mp3_bitrate": {
"enum": [
"64k",
"96k",
"128k",
"192k"
],
"type": "string",
"title": "mp3_bitrate",
"description": "Bitrate used when output_format is mp3.",
"default": "96k",
"x-order": 8
},
"output_format": {
"enum": [
"mp3",
"wav"
],
"type": "string",
"title": "output_format",
"description": "Audio format of the returned file.",
"default": "mp3",
"x-order": 7
},
"batch_sentences": {
"type": "boolean",
"title": "Batch Sentences",
"default": true,
"x-order": 6,
"description": "Synthesize all sentences in one batched pass. Much faster on GPU."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output",
"format": "uri"
}