usamaehsan/chatterbox-tts-v18
Fast batched multilingual text-to-speech (23 languages) on Chatterbox Multilingual. Preset voice library, no voice cloning, no watermark, max_seconds cap that stops at a sentence end.
Run usamaehsan/chatterbox-tts-v18 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
|
Text to narrate. It is split into sentences and synthesised in one batched pass; max_seconds caps how much of it is spoken.
|
|
| language |
None
|
es
|
Language of the text.
|
| voice |
None
|
default
|
Voice from our library. There is no voice cloning: only the voices listed here exist.
|
| max_seconds |
number
|
60.0
Max: 900.0 |
Longest audio to return, in seconds. Speech stops at the last sentence end that fits. 0 = no cap (the whole text).
|
| exaggeration |
number
|
0.5
Min: 0.25 Max: 2.0 |
Expressiveness. 0.5 is neutral.
|
| cfg_weight |
number
|
0.5
Max: 1.0 |
Pace/guidance. 0 disables CFG and halves the cost.
|
| temperature |
number
|
0.8
Min: 0.05 Max: 5.0 |
None
|
| flow_steps |
integer
|
10
Min: 1.0 Max: 10.0 |
Token-to-mel flow-matching steps. Fewer is cheaper.
|
| chunk_chars |
integer
|
40
Min: 30.0 Max: 300.0 |
Target characters per chunk. Lower means more rows decoded in parallel and a shorter critical path, at some risk of audible seams.
|
| fast |
boolean
|
True
|
Use the hand-written decoder. Off falls back to transformers' eager loop, for comparison.
|
| graph |
boolean
|
False
|
Replay CUDA graphs instead of launching kernels. Experimental and off: capture succeeds but the replayed decode produces non-finite logits, and no graph is captured at boot unless GRAPH=1.
|
| batch_sentences |
boolean
|
True
|
Decode every sentence in one pass. Off synthesises serially, for cost comparison.
|
| silence |
number
|
0.25
Max: 2.0 |
Seconds of silence between sentences.
|
| output_format |
None
|
mp3
|
None
|
| mp3_bitrate |
None
|
96k
|
None
|
| seed |
integer
|
0
|
0 for random.
|
{
"type": "object",
"title": "Input",
"required": [
"text"
],
"properties": {
"fast": {
"type": "boolean",
"title": "Fast",
"default": true,
"x-order": 9,
"description": "Use the hand-written decoder. Off falls back to transformers' eager loop, for comparison."
},
"seed": {
"type": "integer",
"title": "Seed",
"default": 0,
"x-order": 15,
"description": "0 for random."
},
"text": {
"type": "string",
"title": "Text",
"x-order": 0,
"description": "Text to narrate. It is split into sentences and synthesised in one batched pass; max_seconds caps how much of it is spoken."
},
"graph": {
"type": "boolean",
"title": "Graph",
"default": false,
"x-order": 10,
"description": "Replay CUDA graphs instead of launching kernels. Experimental and off: capture succeeds but the replayed decode produces non-finite logits, and no graph is captured at boot unless GRAPH=1."
},
"voice": {
"enum": [
"default",
"british_narrator",
"documentary_male",
"kids_storyteller",
"spanish_grandmother"
],
"type": "string",
"title": "voice",
"description": "Voice from our library. There is no voice cloning: only the voices listed here exist.",
"default": "default",
"x-order": 2
},
"silence": {
"type": "number",
"title": "Silence",
"default": 0.25,
"maximum": 2.0,
"minimum": 0.0,
"x-order": 12,
"description": "Seconds of silence between sentences."
},
"language": {
"enum": [
"ar",
"da",
"de",
"el",
"en",
"es",
"fi",
"fr",
"he",
"hi",
"it",
"ja",
"ko",
"ms",
"nl",
"no",
"pl",
"pt",
"ru",
"sv",
"sw",
"tr",
"zh"
],
"type": "string",
"title": "language",
"description": "Language of the text.",
"default": "es",
"x-order": 1
},
"cfg_weight": {
"type": "number",
"title": "Cfg Weight",
"default": 0.5,
"maximum": 1.0,
"minimum": 0.0,
"x-order": 5,
"description": "Pace/guidance. 0 disables CFG and halves the cost."
},
"flow_steps": {
"type": "integer",
"title": "Flow Steps",
"default": 10,
"maximum": 10.0,
"minimum": 1.0,
"x-order": 7,
"description": "Token-to-mel flow-matching steps. Fewer is cheaper."
},
"chunk_chars": {
"type": "integer",
"title": "Chunk Chars",
"default": 40,
"maximum": 300.0,
"minimum": 30.0,
"x-order": 8,
"description": "Target characters per chunk. Lower means more rows decoded in parallel and a shorter critical path, at some risk of audible seams."
},
"max_seconds": {
"type": "number",
"title": "Max Seconds",
"default": 60.0,
"maximum": 900.0,
"minimum": 0.0,
"x-order": 3,
"description": "Longest audio to return, in seconds. Speech stops at the last sentence end that fits. 0 = no cap (the whole text)."
},
"mp3_bitrate": {
"enum": [
"64k",
"96k",
"128k",
"192k"
],
"type": "string",
"title": "mp3_bitrate",
"description": "An enumeration.",
"default": "96k",
"x-order": 14
},
"temperature": {
"type": "number",
"title": "Temperature",
"default": 0.8,
"maximum": 5.0,
"minimum": 0.05,
"x-order": 6
},
"exaggeration": {
"type": "number",
"title": "Exaggeration",
"default": 0.5,
"maximum": 2.0,
"minimum": 0.25,
"x-order": 4,
"description": "Expressiveness. 0.5 is neutral."
},
"output_format": {
"enum": [
"mp3",
"wav"
],
"type": "string",
"title": "output_format",
"description": "An enumeration.",
"default": "mp3",
"x-order": 13
},
"batch_sentences": {
"type": "boolean",
"title": "Batch Sentences",
"default": true,
"x-order": 11,
"description": "Decode every sentence in one pass. Off synthesises serially, for cost comparison."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output",
"format": "uri"
}