492 lines
24 KiB
JSON
492 lines
24 KiB
JSON
{
|
|
"url": "https://replicate.com/lucataco/xtts-v2",
|
|
"owner": "lucataco",
|
|
"name": "xtts-v2",
|
|
"description": "Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning",
|
|
"visibility": "public",
|
|
"github_url": "https://github.com/lucataco/cog-xtts-v2",
|
|
"paper_url": "https://huggingface.co/coqui/XTTS-v2",
|
|
"license_url": "https://coqui.ai/cpml",
|
|
"run_count": 0,
|
|
"cover_image_url": "https://tjzk.replicate.delivery/models_models_cover_image/760b1398-2ab5-4e9b-959e-f3fed025c82f/xtts.png",
|
|
"default_example": {
|
|
"id": "adinmbzbslyshwze5s6qmpzmzu",
|
|
"model": "lucataco/xtts-v2",
|
|
"version": "49ff6cfa14bd4e7f80f62e2279f82f23dfc2e7970f825f8db5599f8a6213c009",
|
|
"status": "succeeded",
|
|
"input": {
|
|
"text": "Hi there, I'm your new voice clone. Try your best to upload quality audio",
|
|
"speaker": "https://replicate.delivery/pbxt/Jt79w0xsT64R1JsiJ0LQRL8UcWspg5J4RFrU6YwEKpOT1ukS/male.wav",
|
|
"language": "en",
|
|
"cleanup_voice": false
|
|
},
|
|
"output": "https://replicate.delivery/pbxt/eyESqfNPahnLY0gaohu50zm3nL6d5ZLxKdWMuqSPRqbihfxjA/output.wav",
|
|
"logs": "ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers\nbuilt with gcc 11 (Ubuntu 11.2.0-19ubuntu1)\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\nlibavutil 56. 70.100 / 56. 70.100\nlibavcodec 58.134.100 / 58.134.100\nlibavformat 58. 76.100 / 58. 76.100\nlibavdevice 58. 13.100 / 58. 13.100\nlibavfilter 7.110.100 / 7.110.100\nlibswscale 5. 9.100 / 5. 9.100\nlibswresample 3. 9.100 / 3. 9.100\nlibpostproc 55. 9.100 / 55. 9.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmphmw6jd84male.wav':\nMetadata:\nencoder : Lavf58.29.100\nDuration: 00:00:08.64, bitrate: 705 kb/s\nStream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 44100 Hz, mono, s16, 705 kb/s\nStream mapping:\nStream #0:0 -> #0:0 (pcm_s16le (native) -> pcm_s16le (native))\nPress [q] to stop, [?] for help\nOutput #0, wav, to '/tmp/speaker.wav':\nMetadata:\nISFT : Lavf58.76.100\nStream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 44100 Hz, mono, s16, 705 kb/s\nMetadata:\nencoder : Lavc58.134.100 pcm_s16le\nsize= 4kB time=00:00:00.00 bitrate=N/A speed=N/A\nsize= 744kB time=00:00:08.63 bitrate= 705.9kbits/s speed=1.75e+03x\nvideo:0kB audio:744kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.010236%\n> Text splitted to sentences.\n[\"Hi there, I'm your new voice clone.\", 'Try your best to upload quality audio']\n> Processing time: 3.3411097526550293\n> Real-time factor: 0.613438166517148",
|
|
"error": null,
|
|
"metrics": {
|
|
"predict_time": 4.303438,
|
|
"total_time": 4.319136
|
|
},
|
|
"created_at": "2023-11-16T16:42:06.735772Z",
|
|
"started_at": "2023-11-16T16:42:06.751470Z",
|
|
"completed_at": "2023-11-16T16:42:11.054908Z",
|
|
"urls": {
|
|
"get": "https://api.replicate.com/v1/predictions/adinmbzbslyshwze5s6qmpzmzu",
|
|
"cancel": "https://api.replicate.com/v1/predictions/adinmbzbslyshwze5s6qmpzmzu/cancel"
|
|
}
|
|
},
|
|
"latest_version": {
|
|
"id": "684bc3855b37866c0c65add2ff39c78f3dea3f4ff103a436465326e0f438d55e",
|
|
"created_at": "2023-11-28T15:39:16.308105+00:00",
|
|
"cog_version": "0.8.6",
|
|
"openapi_schema": {
|
|
"info": {
|
|
"title": "Cog",
|
|
"version": "0.1.0"
|
|
},
|
|
"paths": {
|
|
"/": {
|
|
"get": {
|
|
"summary": "Root",
|
|
"responses": {
|
|
"200": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"title": "Response Root Get"
|
|
}
|
|
}
|
|
},
|
|
"description": "Successful Response"
|
|
}
|
|
},
|
|
"operationId": "root__get"
|
|
}
|
|
},
|
|
"/shutdown": {
|
|
"post": {
|
|
"summary": "Start Shutdown",
|
|
"responses": {
|
|
"200": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"title": "Response Start Shutdown Shutdown Post"
|
|
}
|
|
}
|
|
},
|
|
"description": "Successful Response"
|
|
}
|
|
},
|
|
"operationId": "start_shutdown_shutdown_post"
|
|
}
|
|
},
|
|
"/predictions": {
|
|
"post": {
|
|
"summary": "Predict",
|
|
"responses": {
|
|
"200": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/PredictionResponse"
|
|
}
|
|
}
|
|
},
|
|
"description": "Successful Response"
|
|
},
|
|
"422": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
},
|
|
"description": "Validation Error"
|
|
}
|
|
},
|
|
"parameters": [
|
|
{
|
|
"in": "header",
|
|
"name": "prefer",
|
|
"schema": {
|
|
"type": "string",
|
|
"title": "Prefer"
|
|
},
|
|
"required": false
|
|
}
|
|
],
|
|
"description": "Run a single prediction on the model",
|
|
"operationId": "predict_predictions_post",
|
|
"requestBody": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/PredictionRequest"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/health-check": {
|
|
"get": {
|
|
"summary": "Healthcheck",
|
|
"responses": {
|
|
"200": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"title": "Response Healthcheck Health Check Get"
|
|
}
|
|
}
|
|
},
|
|
"description": "Successful Response"
|
|
}
|
|
},
|
|
"operationId": "healthcheck_health_check_get"
|
|
}
|
|
},
|
|
"/predictions/{prediction_id}": {
|
|
"put": {
|
|
"summary": "Predict Idempotent",
|
|
"responses": {
|
|
"200": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/PredictionResponse"
|
|
}
|
|
}
|
|
},
|
|
"description": "Successful Response"
|
|
},
|
|
"422": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
},
|
|
"description": "Validation Error"
|
|
}
|
|
},
|
|
"parameters": [
|
|
{
|
|
"in": "path",
|
|
"name": "prediction_id",
|
|
"schema": {
|
|
"type": "string",
|
|
"title": "Prediction ID"
|
|
},
|
|
"required": true
|
|
},
|
|
{
|
|
"in": "header",
|
|
"name": "prefer",
|
|
"schema": {
|
|
"type": "string",
|
|
"title": "Prefer"
|
|
},
|
|
"required": false
|
|
}
|
|
],
|
|
"description": "Run a single prediction on the model (idempotent creation).",
|
|
"operationId": "predict_idempotent_predictions__prediction_id__put",
|
|
"requestBody": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"allOf": [
|
|
{
|
|
"$ref": "#/components/schemas/PredictionRequest"
|
|
}
|
|
],
|
|
"title": "Prediction Request"
|
|
}
|
|
}
|
|
},
|
|
"required": true
|
|
}
|
|
}
|
|
},
|
|
"/predictions/{prediction_id}/cancel": {
|
|
"post": {
|
|
"summary": "Cancel",
|
|
"responses": {
|
|
"200": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"title": "Response Cancel Predictions Prediction Id Cancel Post"
|
|
}
|
|
}
|
|
},
|
|
"description": "Successful Response"
|
|
},
|
|
"422": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
},
|
|
"description": "Validation Error"
|
|
}
|
|
},
|
|
"parameters": [
|
|
{
|
|
"in": "path",
|
|
"name": "prediction_id",
|
|
"schema": {
|
|
"type": "string",
|
|
"title": "Prediction ID"
|
|
},
|
|
"required": true
|
|
}
|
|
],
|
|
"description": "Cancel a running prediction",
|
|
"operationId": "cancel_predictions__prediction_id__cancel_post"
|
|
}
|
|
}
|
|
},
|
|
"openapi": "3.0.2",
|
|
"components": {
|
|
"schemas": {
|
|
"Input": {
|
|
"type": "object",
|
|
"title": "Input",
|
|
"required": [
|
|
"speaker"
|
|
],
|
|
"properties": {
|
|
"text": {
|
|
"type": "string",
|
|
"title": "Text",
|
|
"default": "Hi there, I'm your new voice clone. Try your best to upload quality audio",
|
|
"x-order": 0,
|
|
"description": "Text to synthesize"
|
|
},
|
|
"speaker": {
|
|
"type": "string",
|
|
"title": "Speaker",
|
|
"format": "uri",
|
|
"x-order": 1,
|
|
"description": "Original speaker audio (wav, mp3, m4a, ogg, or flv)"
|
|
},
|
|
"language": {
|
|
"allOf": [
|
|
{
|
|
"$ref": "#/components/schemas/language"
|
|
}
|
|
],
|
|
"default": "en",
|
|
"x-order": 2,
|
|
"description": "Output language for the synthesised speech"
|
|
},
|
|
"cleanup_voice": {
|
|
"type": "boolean",
|
|
"title": "Cleanup Voice",
|
|
"default": false,
|
|
"x-order": 3,
|
|
"description": "Whether to apply denoising to the speaker audio (microphone recordings)"
|
|
}
|
|
}
|
|
},
|
|
"Output": {
|
|
"type": "string",
|
|
"title": "Output",
|
|
"format": "uri"
|
|
},
|
|
"Status": {
|
|
"enum": [
|
|
"starting",
|
|
"processing",
|
|
"succeeded",
|
|
"canceled",
|
|
"failed"
|
|
],
|
|
"type": "string",
|
|
"title": "Status",
|
|
"description": "An enumeration."
|
|
},
|
|
"language": {
|
|
"enum": [
|
|
"en",
|
|
"es",
|
|
"fr",
|
|
"de",
|
|
"it",
|
|
"pt",
|
|
"pl",
|
|
"tr",
|
|
"ru",
|
|
"nl",
|
|
"cs",
|
|
"ar",
|
|
"zh",
|
|
"hu",
|
|
"ko",
|
|
"hi"
|
|
],
|
|
"type": "string",
|
|
"title": "language",
|
|
"description": "An enumeration."
|
|
},
|
|
"WebhookEvent": {
|
|
"enum": [
|
|
"start",
|
|
"output",
|
|
"logs",
|
|
"completed"
|
|
],
|
|
"type": "string",
|
|
"title": "WebhookEvent",
|
|
"description": "An enumeration."
|
|
},
|
|
"ValidationError": {
|
|
"type": "object",
|
|
"title": "ValidationError",
|
|
"required": [
|
|
"loc",
|
|
"msg",
|
|
"type"
|
|
],
|
|
"properties": {
|
|
"loc": {
|
|
"type": "array",
|
|
"items": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "integer"
|
|
}
|
|
]
|
|
},
|
|
"title": "Location"
|
|
},
|
|
"msg": {
|
|
"type": "string",
|
|
"title": "Message"
|
|
},
|
|
"type": {
|
|
"type": "string",
|
|
"title": "Error Type"
|
|
}
|
|
}
|
|
},
|
|
"PredictionRequest": {
|
|
"type": "object",
|
|
"title": "PredictionRequest",
|
|
"properties": {
|
|
"id": {
|
|
"type": "string",
|
|
"title": "Id"
|
|
},
|
|
"input": {
|
|
"$ref": "#/components/schemas/Input"
|
|
},
|
|
"webhook": {
|
|
"type": "string",
|
|
"title": "Webhook",
|
|
"format": "uri",
|
|
"maxLength": 65536,
|
|
"minLength": 1
|
|
},
|
|
"created_at": {
|
|
"type": "string",
|
|
"title": "Created At",
|
|
"format": "date-time"
|
|
},
|
|
"output_file_prefix": {
|
|
"type": "string",
|
|
"title": "Output File Prefix"
|
|
},
|
|
"webhook_events_filter": {
|
|
"type": "array",
|
|
"items": {
|
|
"$ref": "#/components/schemas/WebhookEvent"
|
|
},
|
|
"default": [
|
|
"start",
|
|
"output",
|
|
"logs",
|
|
"completed"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"PredictionResponse": {
|
|
"type": "object",
|
|
"title": "PredictionResponse",
|
|
"properties": {
|
|
"id": {
|
|
"type": "string",
|
|
"title": "Id"
|
|
},
|
|
"logs": {
|
|
"type": "string",
|
|
"title": "Logs",
|
|
"default": ""
|
|
},
|
|
"error": {
|
|
"type": "string",
|
|
"title": "Error"
|
|
},
|
|
"input": {
|
|
"$ref": "#/components/schemas/Input"
|
|
},
|
|
"output": {
|
|
"$ref": "#/components/schemas/Output"
|
|
},
|
|
"status": {
|
|
"$ref": "#/components/schemas/Status"
|
|
},
|
|
"metrics": {
|
|
"type": "object",
|
|
"title": "Metrics"
|
|
},
|
|
"version": {
|
|
"type": "string",
|
|
"title": "Version"
|
|
},
|
|
"created_at": {
|
|
"type": "string",
|
|
"title": "Created At",
|
|
"format": "date-time"
|
|
},
|
|
"started_at": {
|
|
"type": "string",
|
|
"title": "Started At",
|
|
"format": "date-time"
|
|
},
|
|
"completed_at": {
|
|
"type": "string",
|
|
"title": "Completed At",
|
|
"format": "date-time"
|
|
}
|
|
}
|
|
},
|
|
"HTTPValidationError": {
|
|
"type": "object",
|
|
"title": "HTTPValidationError",
|
|
"properties": {
|
|
"detail": {
|
|
"type": "array",
|
|
"items": {
|
|
"$ref": "#/components/schemas/ValidationError"
|
|
},
|
|
"title": "Detail"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |