chenxwh
/
openvoice
Updated to OpenVoice v2: Versatile Instant Voice Cloning
Prediction
chenxwh/openvoice:d548923cIDmtnb5fpqasrgj0cf4p4b2sp1ymStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- text
- El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante.
- audio
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- speed
- 1
- language
- ES
{ "text": "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante.", "audio": "https://replicate.delivery/pbxt/KpK8evnazh2CSvXSeEpVA12nr8U7by0LBguRu1mF5tzMWr2D/example_reference.mp3", "speed": 1, "language": "ES" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", { input: { text: "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante.", audio: "https://replicate.delivery/pbxt/KpK8evnazh2CSvXSeEpVA12nr8U7by0LBguRu1mF5tzMWr2D/example_reference.mp3", speed: 1, language: "ES" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", input={ "text": "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante.", "audio": "https://replicate.delivery/pbxt/KpK8evnazh2CSvXSeEpVA12nr8U7by0LBguRu1mF5tzMWr2D/example_reference.mp3", "speed": 1, "language": "ES" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", "input": { "text": "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante.", "audio": "https://replicate.delivery/pbxt/KpK8evnazh2CSvXSeEpVA12nr8U7by0LBguRu1mF5tzMWr2D/example_reference.mp3", "speed": 1, "language": "ES" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2024-04-28T16:28:11.821113Z", "created_at": "2024-04-28T16:27:56.118000Z", "data_removed": false, "error": null, "id": "mtnb5fpqasrgj0cf4p4b2sp1ym", "input": { "text": "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante.", "audio": "https://replicate.delivery/pbxt/KpK8evnazh2CSvXSeEpVA12nr8U7by0LBguRu1mF5tzMWr2D/example_reference.mp3", "speed": 1, "language": "ES" }, "logs": "OpenVoice version: v2\n> Text split to sentences.\nEl resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante.\n> ===========================\n 0%| | 0/1 [00:00<?, ?it/s]\n100%|██████████| 1/1 [00:07<00:00, 7.33s/it]\n100%|██████████| 1/1 [00:07<00:00, 7.33s/it]", "metrics": { "predict_time": 15.66556, "total_time": 15.703113 }, "output": "https://replicate.delivery/pbxt/elqQhdCLRB16ekw8o0a0i2e7iVJdxV18j7W1f1YmLieVjV4VC/out.wav", "started_at": "2024-04-28T16:27:56.155553Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/mtnb5fpqasrgj0cf4p4b2sp1ym", "cancel": "https://api.replicate.com/v1/predictions/mtnb5fpqasrgj0cf4p4b2sp1ym/cancel" }, "version": "002cf9fb1ac44f6a172c4ceb868df704a414a8346ac0296310a2d1207226d3a2" }
Generated inOpenVoice version: v2 > Text split to sentences. El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante. > =========================== 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████| 1/1 [00:07<00:00, 7.33s/it] 100%|██████████| 1/1 [00:07<00:00, 7.33s/it]
Prediction
chenxwh/openvoice:d548923cID0qb082sjxxrgm0cf4p5ad8r2xrStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- text
- 这次旅行我们计划去巴黎欣赏埃菲尔铁塔和卢浮宫的美景
- audio
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- speed
- 1
- language
- ZH
{ "text": "这次旅行我们计划去巴黎欣赏埃菲尔铁塔和卢浮宫的美景", "audio": "https://replicate.delivery/pbxt/KpKA3E3rxf1iTgrvipsYfzQ7K3PhD6NiuCavVn5BBAMiL6wZ/example_reference.mp3", "speed": 1, "language": "ZH" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", { input: { text: "这次旅行我们计划去巴黎欣赏埃菲尔铁塔和卢浮宫的美景", audio: "https://replicate.delivery/pbxt/KpKA3E3rxf1iTgrvipsYfzQ7K3PhD6NiuCavVn5BBAMiL6wZ/example_reference.mp3", speed: 1, language: "ZH" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", input={ "text": "这次旅行我们计划去巴黎欣赏埃菲尔铁塔和卢浮宫的美景", "audio": "https://replicate.delivery/pbxt/KpKA3E3rxf1iTgrvipsYfzQ7K3PhD6NiuCavVn5BBAMiL6wZ/example_reference.mp3", "speed": 1, "language": "ZH" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", "input": { "text": "这次旅行我们计划去巴黎欣赏埃菲尔铁塔和卢浮宫的美景", "audio": "https://replicate.delivery/pbxt/KpKA3E3rxf1iTgrvipsYfzQ7K3PhD6NiuCavVn5BBAMiL6wZ/example_reference.mp3", "speed": 1, "language": "ZH" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2024-04-28T16:29:39.624105Z", "created_at": "2024-04-28T16:29:25.103000Z", "data_removed": false, "error": null, "id": "0qb082sjxxrgm0cf4p5ad8r2xr", "input": { "text": "这次旅行我们计划去巴黎欣赏埃菲尔铁塔和卢浮宫的美景", "audio": "https://replicate.delivery/pbxt/KpKA3E3rxf1iTgrvipsYfzQ7K3PhD6NiuCavVn5BBAMiL6wZ/example_reference.mp3", "speed": 1, "language": "ZH" }, "logs": "OpenVoice version: v2\n> Text split to sentences.\n这次旅行我们计划去巴黎欣赏埃菲尔铁塔和卢浮宫的美景\n> ===========================\n0%| | 0/1 [00:00<?, ?it/s]Building prefix dict from the default dictionary ...\nDumping model to file cache /tmp/jieba.cache\nLoading model cost 0.624 seconds.\nPrefix dict has been built successfully.\nSome weights of the model checkpoint at bert-base-multilingual-uncased were not used when initializing BertForMaskedLM: ['cls.seq_relationship.weight', 'cls.seq_relationship.bias']\n- This IS expected if you are initializing BertForMaskedLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n- This IS NOT expected if you are initializing BertForMaskedLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n100%|██████████| 1/1 [00:06<00:00, 6.32s/it]\n100%|██████████| 1/1 [00:06<00:00, 6.32s/it]", "metrics": { "predict_time": 14.482925, "total_time": 14.521105 }, "output": "https://replicate.delivery/pbxt/hEAqkV4DVe0qTCYFqCtolCB0SPV2nEhbO6BzS8eYbGXytCvSA/out.wav", "started_at": "2024-04-28T16:29:25.141180Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/0qb082sjxxrgm0cf4p5ad8r2xr", "cancel": "https://api.replicate.com/v1/predictions/0qb082sjxxrgm0cf4p5ad8r2xr/cancel" }, "version": "002cf9fb1ac44f6a172c4ceb868df704a414a8346ac0296310a2d1207226d3a2" }
Generated inOpenVoice version: v2 > Text split to sentences. 这次旅行我们计划去巴黎欣赏埃菲尔铁塔和卢浮宫的美景 > =========================== 0%| | 0/1 [00:00<?, ?it/s]Building prefix dict from the default dictionary ... Dumping model to file cache /tmp/jieba.cache Loading model cost 0.624 seconds. Prefix dict has been built successfully. Some weights of the model checkpoint at bert-base-multilingual-uncased were not used when initializing BertForMaskedLM: ['cls.seq_relationship.weight', 'cls.seq_relationship.bias'] - This IS expected if you are initializing BertForMaskedLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertForMaskedLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). 100%|██████████| 1/1 [00:06<00:00, 6.32s/it] 100%|██████████| 1/1 [00:06<00:00, 6.32s/it]
Prediction
chenxwh/openvoice:d548923cID5lkp6zlbc3wnxicyqhlvhospmmStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- audio
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- speed
- 1
- style
- whispering
- prompt
- This audio is generated by open voice with a half-performance model.
- agree_terms
- true
{ "audio": "https://replicate.delivery/pbxt/KB9Q5ER6n39loKuLKdkmPlOr8uR0eCNHY9dFYZQvL3MIfsBH/demo_speaker2.mp3", "speed": 1, "style": "whispering", "prompt": "This audio is generated by open voice with a half-performance model.", "agree_terms": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", { input: { audio: "https://replicate.delivery/pbxt/KB9Q5ER6n39loKuLKdkmPlOr8uR0eCNHY9dFYZQvL3MIfsBH/demo_speaker2.mp3", speed: 1 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", input={ "audio": "https://replicate.delivery/pbxt/KB9Q5ER6n39loKuLKdkmPlOr8uR0eCNHY9dFYZQvL3MIfsBH/demo_speaker2.mp3", "speed": 1 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", "input": { "audio": "https://replicate.delivery/pbxt/KB9Q5ER6n39loKuLKdkmPlOr8uR0eCNHY9dFYZQvL3MIfsBH/demo_speaker2.mp3", "speed": 1 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2024-01-06T12:13:07.580462Z", "created_at": "2024-01-06T12:13:04.504583Z", "data_removed": false, "error": null, "id": "5lkp6zlbc3wnxicyqhlvhospmm", "input": { "audio": "https://replicate.delivery/pbxt/KB9Q5ER6n39loKuLKdkmPlOr8uR0eCNHY9dFYZQvL3MIfsBH/demo_speaker2.mp3", "speed": 1, "style": "whispering", "prompt": "This audio is generated by open voice with a half-performance model.", "agree_terms": true }, "logs": "Detected language:en\n[(0.0, 8.178), (9.326, 12.914), (13.262, 16.402), (16.654, 29.49225)]\nafter vad: dur = 27.743990929705216\n> Text splitted to sentences.\nThis audio is generated by open voice with a half-performance model.\n> ===========================\nðɪs ˈɑdiˌoʊ ɪz ˈdʒɛnəɹˌeɪtɪd baɪ ˈoʊpən vɔɪs wɪθ ə half-peɹfoɹmance* ˈmɑdəɫ.\nlength:76\nlength:75", "metrics": { "predict_time": 3.020889, "total_time": 3.075879 }, "output": "https://replicate.delivery/pbxt/Z41YrcHtRhbkNVKD2TMeUG0eF6jBEXE3B8B45HGWLS8SXvJSA/out.wav", "started_at": "2024-01-06T12:13:04.559573Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/5lkp6zlbc3wnxicyqhlvhospmm", "cancel": "https://api.replicate.com/v1/predictions/5lkp6zlbc3wnxicyqhlvhospmm/cancel" }, "version": "bafe15fd0223c29cdfbb50d5cbc3feb1b1706f6d358ffe057a81d03577229143" }
Generated inDetected language:en [(0.0, 8.178), (9.326, 12.914), (13.262, 16.402), (16.654, 29.49225)] after vad: dur = 27.743990929705216 > Text splitted to sentences. This audio is generated by open voice with a half-performance model. > =========================== ðɪs ˈɑdiˌoʊ ɪz ˈdʒɛnəɹˌeɪtɪd baɪ ˈoʊpən vɔɪs wɪθ ə half-peɹfoɹmance* ˈmɑdəɫ. length:76 length:75
Prediction
chenxwh/openvoice:d548923cIDt3nzzrlbipkrkz3xyt7cfnml2yStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- audio
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- speed
- 1
- style
- default
- prompt
- This audio is generated by OpenVoice.
- agree_terms
- true
{ "audio": "https://replicate.delivery/pbxt/KB9SF5XxN60ce4LlOoDBQ3Si1cmwGmTQ4wPYf4cyURovXJ9b/example_reference.mp3", "speed": 1, "style": "default", "prompt": "This audio is generated by OpenVoice.", "agree_terms": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", { input: { audio: "https://replicate.delivery/pbxt/KB9SF5XxN60ce4LlOoDBQ3Si1cmwGmTQ4wPYf4cyURovXJ9b/example_reference.mp3", speed: 1 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", input={ "audio": "https://replicate.delivery/pbxt/KB9SF5XxN60ce4LlOoDBQ3Si1cmwGmTQ4wPYf4cyURovXJ9b/example_reference.mp3", "speed": 1 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", "input": { "audio": "https://replicate.delivery/pbxt/KB9SF5XxN60ce4LlOoDBQ3Si1cmwGmTQ4wPYf4cyURovXJ9b/example_reference.mp3", "speed": 1 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2024-01-06T12:16:04.855305Z", "created_at": "2024-01-06T12:15:21.363468Z", "data_removed": false, "error": null, "id": "t3nzzrlbipkrkz3xyt7cfnml2y", "input": { "audio": "https://replicate.delivery/pbxt/KB9SF5XxN60ce4LlOoDBQ3Si1cmwGmTQ4wPYf4cyURovXJ9b/example_reference.mp3", "speed": 1, "style": "default", "prompt": "This audio is generated by OpenVoice.", "agree_terms": true }, "logs": "Detected language:en\n/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torch/hub.py:267: UserWarning: You are about to download and run code from an untrusted repository. In a future release, this won't be allowed. To add the repository to your trusted list, change the command to {calling_fn}(..., trust_repo=False) and a command prompt will appear asking for an explicit confirmation of trust, or load(..., trust_repo=True), which will assume that the prompt is to be answered with 'yes'. You can also use load(..., trust_repo='check') which will only prompt for confirmation if the repo is not already trusted. This will eventually be the default behaviour\nwarnings.warn(\nDownloading: \"https://github.com/snakers4/silero-vad/zipball/master\" to /root/.cache/torch/hub/master.zip\n[(0.0, 14.5666875)]\nafter vad: dur = 14.566\n> Text splitted to sentences.\nThis audio is generated by OpenVoice.\n> ===========================\nðɪs ˈɑdiˌoʊ ɪz ˈdʒɛnəɹˌeɪtɪd baɪ ˈoʊpən vɔɪs.\nlength:45\nlength:45\n/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/wavmark/models/my_model.py:25: UserWarning: istft will require a complex-valued input tensor in a future PyTorch release. Matching the output from stft with return_complex=True. (Triggered internally at ../aten/src/ATen/native/SpectralOps.cpp:978.)\nreturn torch.istft(signal_wmd_fft, n_fft=self.n_fft, hop_length=self.hop_length, window=window,", "metrics": { "predict_time": 7.420476, "total_time": 43.491837 }, "output": "https://replicate.delivery/pbxt/I7ilEvNWhRYXC90f12pexJTubezz3Adr7MuAzCFtomwG0emIB/out.wav", "started_at": "2024-01-06T12:15:57.434829Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/t3nzzrlbipkrkz3xyt7cfnml2y", "cancel": "https://api.replicate.com/v1/predictions/t3nzzrlbipkrkz3xyt7cfnml2y/cancel" }, "version": "af9877f21c4e040357eb6424ecddd7199367be2d8667ad4b6bbd306cbcd326e4" }
Generated inDetected language:en /root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torch/hub.py:267: UserWarning: You are about to download and run code from an untrusted repository. In a future release, this won't be allowed. To add the repository to your trusted list, change the command to {calling_fn}(..., trust_repo=False) and a command prompt will appear asking for an explicit confirmation of trust, or load(..., trust_repo=True), which will assume that the prompt is to be answered with 'yes'. You can also use load(..., trust_repo='check') which will only prompt for confirmation if the repo is not already trusted. This will eventually be the default behaviour warnings.warn( Downloading: "https://github.com/snakers4/silero-vad/zipball/master" to /root/.cache/torch/hub/master.zip [(0.0, 14.5666875)] after vad: dur = 14.566 > Text splitted to sentences. This audio is generated by OpenVoice. > =========================== ðɪs ˈɑdiˌoʊ ɪz ˈdʒɛnəɹˌeɪtɪd baɪ ˈoʊpən vɔɪs. length:45 length:45 /root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/wavmark/models/my_model.py:25: UserWarning: istft will require a complex-valued input tensor in a future PyTorch release. Matching the output from stft with return_complex=True. (Triggered internally at ../aten/src/ATen/native/SpectralOps.cpp:978.) return torch.istft(signal_wmd_fft, n_fft=self.n_fft, hop_length=self.hop_length, window=window,
Prediction
chenxwh/openvoice:d548923cIDbdvzpotb7p6fq3tokdpazbiloqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- audio
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- speed
- 1
- style
- default
- prompt
- He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce.
- agree_terms
- true
{ "audio": "https://replicate.delivery/pbxt/KB9Tfj0o8VwpnYirmw4Jjz6OeShKvw3XHoVLTSBkBYoL8DRq/demo_speaker1.mp3", "speed": 1, "style": "default", "prompt": "He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce.", "agree_terms": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", { input: { audio: "https://replicate.delivery/pbxt/KB9Tfj0o8VwpnYirmw4Jjz6OeShKvw3XHoVLTSBkBYoL8DRq/demo_speaker1.mp3", speed: 1 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", input={ "audio": "https://replicate.delivery/pbxt/KB9Tfj0o8VwpnYirmw4Jjz6OeShKvw3XHoVLTSBkBYoL8DRq/demo_speaker1.mp3", "speed": 1 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", "input": { "audio": "https://replicate.delivery/pbxt/KB9Tfj0o8VwpnYirmw4Jjz6OeShKvw3XHoVLTSBkBYoL8DRq/demo_speaker1.mp3", "speed": 1 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2024-01-06T12:16:57.006690Z", "created_at": "2024-01-06T12:16:51.648010Z", "data_removed": false, "error": null, "id": "bdvzpotb7p6fq3tokdpazbiloq", "input": { "audio": "https://replicate.delivery/pbxt/KB9Tfj0o8VwpnYirmw4Jjz6OeShKvw3XHoVLTSBkBYoL8DRq/demo_speaker1.mp3", "speed": 1, "style": "default", "prompt": "He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce.", "agree_terms": true }, "logs": "Detected language:en\n[(0.43, 13.97), (14.51, 29.682), (29.966, 40.722), (41.038, 54.29), (55.086, 59.218), (59.662, 61.266), (62.51, 67.314), (67.438, 69.042), (69.646, 79.442), (80.334, 86.386), (86.414, 91.090875)]\nafter vad: dur = 85.38802721088436\n> Text splitted to sentences.\nHe hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick,\npeppered, flour-fattened sauce.\n> ===========================\nhi hoʊpt ðɛɹ wʊd bi stu fəɹ ˈdɪnəɹ, ˈtəɹnəps ənd ˈkɛɹəts ənd bɹuzd pəˈteɪtoʊz ənd fæt ˈmətən ˈpisɪz tɪ bi ˈleɪdəɫd aʊt ɪn θɪk,\nlength:126\nlength:126\nˈpɛpəɹd, flouɹ-fattened* sɔs.\nlength:29\nlength:29", "metrics": { "predict_time": 5.325492, "total_time": 5.35868 }, "output": "https://replicate.delivery/pbxt/W61TUeFTmW3ZY63z1ooNrzzgYeB2mYeqYaOC3fNUBlmgr9mIB/out.wav", "started_at": "2024-01-06T12:16:51.681198Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/bdvzpotb7p6fq3tokdpazbiloq", "cancel": "https://api.replicate.com/v1/predictions/bdvzpotb7p6fq3tokdpazbiloq/cancel" }, "version": "af9877f21c4e040357eb6424ecddd7199367be2d8667ad4b6bbd306cbcd326e4" }
Generated inDetected language:en [(0.43, 13.97), (14.51, 29.682), (29.966, 40.722), (41.038, 54.29), (55.086, 59.218), (59.662, 61.266), (62.51, 67.314), (67.438, 69.042), (69.646, 79.442), (80.334, 86.386), (86.414, 91.090875)] after vad: dur = 85.38802721088436 > Text splitted to sentences. He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce. > =========================== hi hoʊpt ðɛɹ wʊd bi stu fəɹ ˈdɪnəɹ, ˈtəɹnəps ənd ˈkɛɹəts ənd bɹuzd pəˈteɪtoʊz ənd fæt ˈmətən ˈpisɪz tɪ bi ˈleɪdəɫd aʊt ɪn θɪk, length:126 length:126 ˈpɛpəɹd, flouɹ-fattened* sɔs. length:29 length:29
Prediction
chenxwh/openvoice:d548923cIDga3qc6tbckhpwaqavboxux2h7mStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- audio
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- speed
- 0.5
- style
- sad
- prompt
- He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce.
- agree_terms
- true
{ "audio": "https://replicate.delivery/pbxt/KB9UuCS6ulvsb0gX8ISkVMrEy8Rr60SF9u0SlsWBxdat2Whi/demo_speaker1.mp3", "speed": 0.5, "style": "sad", "prompt": "He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce.", "agree_terms": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", { input: { audio: "https://replicate.delivery/pbxt/KB9UuCS6ulvsb0gX8ISkVMrEy8Rr60SF9u0SlsWBxdat2Whi/demo_speaker1.mp3", speed: 0.5 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", input={ "audio": "https://replicate.delivery/pbxt/KB9UuCS6ulvsb0gX8ISkVMrEy8Rr60SF9u0SlsWBxdat2Whi/demo_speaker1.mp3", "speed": 0.5 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", "input": { "audio": "https://replicate.delivery/pbxt/KB9UuCS6ulvsb0gX8ISkVMrEy8Rr60SF9u0SlsWBxdat2Whi/demo_speaker1.mp3", "speed": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2024-01-06T12:18:15.096566Z", "created_at": "2024-01-06T12:18:09.714462Z", "data_removed": false, "error": null, "id": "ga3qc6tbckhpwaqavboxux2h7m", "input": { "audio": "https://replicate.delivery/pbxt/KB9UuCS6ulvsb0gX8ISkVMrEy8Rr60SF9u0SlsWBxdat2Whi/demo_speaker1.mp3", "speed": 0.5, "style": "sad", "prompt": "He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce.", "agree_terms": true }, "logs": "Detected language:en\n[(0.43, 13.97), (14.51, 29.682), (29.966, 40.722), (41.038, 54.29), (55.086, 59.218), (59.662, 61.266), (62.51, 67.314), (67.438, 69.042), (69.646, 79.442), (80.334, 86.386), (86.414, 91.090875)]\nafter vad: dur = 85.38802721088436\n> Text splitted to sentences.\nHe hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick,\npeppered, flour-fattened sauce.\n> ===========================\nhi hoʊpt ðɛɹ wʊd bi stu fəɹ ˈdɪnəɹ, ˈtəɹnəps ənd ˈkɛɹəts ənd bɹuzd pəˈteɪtoʊz ənd fæt ˈmətən ˈpisɪz tɪ bi ˈleɪdəɫd aʊt ɪn θɪk,\nlength:126\nlength:126\nˈpɛpəɹd, flouɹ-fattened* sɔs.\nlength:29\nlength:29", "metrics": { "predict_time": 5.336348, "total_time": 5.382104 }, "output": "https://replicate.delivery/pbxt/Y7f1ENgZSzUUAyaDqRseIyXfjufweTmuyendslYo0YOoB3biE/out.wav", "started_at": "2024-01-06T12:18:09.760218Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ga3qc6tbckhpwaqavboxux2h7m", "cancel": "https://api.replicate.com/v1/predictions/ga3qc6tbckhpwaqavboxux2h7m/cancel" }, "version": "af9877f21c4e040357eb6424ecddd7199367be2d8667ad4b6bbd306cbcd326e4" }
Generated inDetected language:en [(0.43, 13.97), (14.51, 29.682), (29.966, 40.722), (41.038, 54.29), (55.086, 59.218), (59.662, 61.266), (62.51, 67.314), (67.438, 69.042), (69.646, 79.442), (80.334, 86.386), (86.414, 91.090875)] after vad: dur = 85.38802721088436 > Text splitted to sentences. He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce. > =========================== hi hoʊpt ðɛɹ wʊd bi stu fəɹ ˈdɪnəɹ, ˈtəɹnəps ənd ˈkɛɹəts ənd bɹuzd pəˈteɪtoʊz ənd fæt ˈmətən ˈpisɪz tɪ bi ˈleɪdəɫd aʊt ɪn θɪk, length:126 length:126 ˈpɛpəɹd, flouɹ-fattened* sɔs. length:29 length:29
Prediction
chenxwh/openvoice:d548923cIDdhvcmwlbkwbk5ameolyifbeccyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- audio
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- speed
- 1
- style
- friendly
- prompt
- OpenVoice enables granular control over voice styles, including emotion, accent, rhythm, pauses, and intonation, in addition to replicating the tone color of the reference speaker.
- agree_terms
- true
{ "audio": "https://replicate.delivery/pbxt/KB9YGZ4v1woTUDd8rSRlizdqIQjxqGjDnosgvlQkTZo7IRI7/demo_speaker0.mp3", "speed": 1, "style": "friendly", "prompt": "OpenVoice enables granular control over voice styles, including emotion, accent, rhythm, pauses, and intonation, in addition to replicating the tone color of the reference speaker.", "agree_terms": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", { input: { audio: "https://replicate.delivery/pbxt/KB9YGZ4v1woTUDd8rSRlizdqIQjxqGjDnosgvlQkTZo7IRI7/demo_speaker0.mp3", speed: 1 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", input={ "audio": "https://replicate.delivery/pbxt/KB9YGZ4v1woTUDd8rSRlizdqIQjxqGjDnosgvlQkTZo7IRI7/demo_speaker0.mp3", "speed": 1 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", "input": { "audio": "https://replicate.delivery/pbxt/KB9YGZ4v1woTUDd8rSRlizdqIQjxqGjDnosgvlQkTZo7IRI7/demo_speaker0.mp3", "speed": 1 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2024-01-06T12:21:44.891938Z", "created_at": "2024-01-06T12:21:42.155130Z", "data_removed": false, "error": null, "id": "dhvcmwlbkwbk5ameolyifbeccy", "input": { "audio": "https://replicate.delivery/pbxt/KB9YGZ4v1woTUDd8rSRlizdqIQjxqGjDnosgvlQkTZo7IRI7/demo_speaker0.mp3", "speed": 1, "style": "friendly", "prompt": "OpenVoice enables granular control over voice styles, including emotion, accent, rhythm, pauses, and intonation, in addition to replicating the tone color of the reference speaker.", "agree_terms": true }, "logs": "Detected language:en\n[(0.0, 19.278375)]\nafter vad: dur = 19.27798185941043\n> Text splitted to sentences.\nOpenVoice enables granular control over voice styles, including emotion, accent, rhythm,\npauses, and intonation, in addition to replicating the tone color of the reference speaker.\n> ===========================\nˈoʊpən vɔɪs ɪˈneɪbəɫz ˈgɹænjələɹ kənˈtɹoʊɫ ˈoʊvəɹ vɔɪs staɪɫz, ˌɪnˈkludɪŋ ˈiˌmoʊʃən, ˈækˌsɛnt, ˈɹɪðəm,\nlength:102\nlength:102\nˈpɔzɪz, ənd ˌɪntəˈneɪʃən, ɪn əˈdɪʃən tɪ ˈɹɛplɪˌkeɪtɪŋ ðə toʊn ˈkələɹ əv ðə ˈɹɛfəɹəns ˈspikəɹ.\nlength:93\nlength:93", "metrics": { "predict_time": 2.6993, "total_time": 2.736808 }, "output": "https://replicate.delivery/pbxt/pYqzoAb4CwrfPSdjMWPrG4TsYLpMHkwyuQBoWhZBsJAsv3EJA/out.wav", "started_at": "2024-01-06T12:21:42.192638Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/dhvcmwlbkwbk5ameolyifbeccy", "cancel": "https://api.replicate.com/v1/predictions/dhvcmwlbkwbk5ameolyifbeccy/cancel" }, "version": "af9877f21c4e040357eb6424ecddd7199367be2d8667ad4b6bbd306cbcd326e4" }
Generated inDetected language:en [(0.0, 19.278375)] after vad: dur = 19.27798185941043 > Text splitted to sentences. OpenVoice enables granular control over voice styles, including emotion, accent, rhythm, pauses, and intonation, in addition to replicating the tone color of the reference speaker. > =========================== ˈoʊpən vɔɪs ɪˈneɪbəɫz ˈgɹænjələɹ kənˈtɹoʊɫ ˈoʊvəɹ vɔɪs staɪɫz, ˌɪnˈkludɪŋ ˈiˌmoʊʃən, ˈækˌsɛnt, ˈɹɪðəm, length:102 length:102 ˈpɔzɪz, ənd ˌɪntəˈneɪʃən, ɪn əˈdɪʃən tɪ ˈɹɛplɪˌkeɪtɪŋ ðə toʊn ˈkələɹ əv ðə ˈɹɛfəɹəns ˈspikəɹ. length:93 length:93
Prediction
chenxwh/openvoice:d548923cIDuaq3y33btmmq53azyj7k7awltqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- audio
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- speed
- 1.2
- style
- cheerful
- prompt
- We introduce OpenVoice, a versatile instant voice cloning approach that requires only a short audio clip from the reference speaker to replicate their voice and generate speech in multiple languages.
- agree_terms
- true
{ "audio": "https://replicate.delivery/pbxt/KB9VsDHTIOZ4th7NjHQLLblrI9Wc5w9BhCOmZXTo71Os6Khr/demo_speaker2.mp3", "speed": 1.2, "style": "cheerful", "prompt": "We introduce OpenVoice, a versatile instant voice cloning approach that requires only a short audio clip from the reference speaker to replicate their voice and generate speech in multiple languages.", "agree_terms": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", { input: { audio: "https://replicate.delivery/pbxt/KB9VsDHTIOZ4th7NjHQLLblrI9Wc5w9BhCOmZXTo71Os6Khr/demo_speaker2.mp3", speed: 1.2 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", input={ "audio": "https://replicate.delivery/pbxt/KB9VsDHTIOZ4th7NjHQLLblrI9Wc5w9BhCOmZXTo71Os6Khr/demo_speaker2.mp3", "speed": 1.2 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", "input": { "audio": "https://replicate.delivery/pbxt/KB9VsDHTIOZ4th7NjHQLLblrI9Wc5w9BhCOmZXTo71Os6Khr/demo_speaker2.mp3", "speed": 1.2 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2024-01-06T12:19:13.478155Z", "created_at": "2024-01-06T12:19:10.374983Z", "data_removed": false, "error": null, "id": "uaq3y33btmmq53azyj7k7awltq", "input": { "audio": "https://replicate.delivery/pbxt/KB9VsDHTIOZ4th7NjHQLLblrI9Wc5w9BhCOmZXTo71Os6Khr/demo_speaker2.mp3", "speed": 1.2, "style": "cheerful", "prompt": "We introduce OpenVoice, a versatile instant voice cloning approach that requires only a short audio clip from the reference speaker to replicate their voice and generate speech in multiple languages.", "agree_terms": true }, "logs": "Detected language:en\n[(0.0, 8.178), (9.326, 12.914), (13.262, 16.402), (16.654, 29.49225)]\nafter vad: dur = 27.743990929705216\n> Text splitted to sentences.\nWe introduce OpenVoice, a versatile instant voice cloning approach that requires only a short audio clip from the reference speaker to replicate their voice and generate speech in multiple languages.\n> ===========================\nwi ˌɪntɹəˈdus ˈoʊpən vɔɪs, ə ˈvəɹsətəɫ ˈɪnstənt vɔɪs ˈkloʊnɪŋ əˈpɹoʊtʃ ðət ɹikˈwaɪəɹz ˈoʊnli ə ʃɔɹt ˈɑdiˌoʊ klɪp fɹəm ðə ˈɹɛfəɹəns ˈspikəɹ tɪ ˈɹɛplɪˌkeɪt ðɛɹ vɔɪs ənd ˈdʒɛnəɹˌeɪt spitʃ ɪn ˈməltəpəɫ ˈlæŋgwɪdʒɪz.\nlength:210\nlength:210", "metrics": { "predict_time": 3.070344, "total_time": 3.103172 }, "output": "https://replicate.delivery/pbxt/CzAXosX7A141KJef0zrlj4SYIbSsnAFWeQ5Y8ZStnChA6emIB/out.wav", "started_at": "2024-01-06T12:19:10.407811Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/uaq3y33btmmq53azyj7k7awltq", "cancel": "https://api.replicate.com/v1/predictions/uaq3y33btmmq53azyj7k7awltq/cancel" }, "version": "af9877f21c4e040357eb6424ecddd7199367be2d8667ad4b6bbd306cbcd326e4" }
Generated inDetected language:en [(0.0, 8.178), (9.326, 12.914), (13.262, 16.402), (16.654, 29.49225)] after vad: dur = 27.743990929705216 > Text splitted to sentences. We introduce OpenVoice, a versatile instant voice cloning approach that requires only a short audio clip from the reference speaker to replicate their voice and generate speech in multiple languages. > =========================== wi ˌɪntɹəˈdus ˈoʊpən vɔɪs, ə ˈvəɹsətəɫ ˈɪnstənt vɔɪs ˈkloʊnɪŋ əˈpɹoʊtʃ ðət ɹikˈwaɪəɹz ˈoʊnli ə ʃɔɹt ˈɑdiˌoʊ klɪp fɹəm ðə ˈɹɛfəɹəns ˈspikəɹ tɪ ˈɹɛplɪˌkeɪt ðɛɹ vɔɪs ənd ˈdʒɛnəɹˌeɪt spitʃ ɪn ˈməltəpəɫ ˈlæŋgwɪdʒɪz. length:210 length:210
Prediction
chenxwh/openvoice:d548923cID1tmwsj9ehhrgj0cfhbft0zthjwStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- text
- Did you ever hear a folk tale about a giant turtle?
- audio
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- speed
- 1
- language
- EN_NEWEST
{ "text": "Did you ever hear a folk tale about a giant turtle?", "audio": "https://replicate.delivery/pbxt/KpK4hkLwhVAJE9K0DAbZP3YfwLzJyLl09kuPnc4MvCYLcX8m/example_reference.mp3", "speed": 1, "language": "EN_NEWEST" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", { input: { text: "Did you ever hear a folk tale about a giant turtle?", audio: "https://replicate.delivery/pbxt/KpK4hkLwhVAJE9K0DAbZP3YfwLzJyLl09kuPnc4MvCYLcX8m/example_reference.mp3", speed: 1, language: "EN_NEWEST" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/openvoice:d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", input={ "text": "Did you ever hear a folk tale about a giant turtle?", "audio": "https://replicate.delivery/pbxt/KpK4hkLwhVAJE9K0DAbZP3YfwLzJyLl09kuPnc4MvCYLcX8m/example_reference.mp3", "speed": 1, "language": "EN_NEWEST" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/openvoice using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d", "input": { "text": "Did you ever hear a folk tale about a giant turtle?", "audio": "https://replicate.delivery/pbxt/KpK4hkLwhVAJE9K0DAbZP3YfwLzJyLl09kuPnc4MvCYLcX8m/example_reference.mp3", "speed": 1, "language": "EN_NEWEST" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream Type LIVERemaining Time -00:00:0001x- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2024-05-18T08:43:59.200172Z", "created_at": "2024-05-18T08:43:53.356000Z", "data_removed": false, "error": null, "id": "1tmwsj9ehhrgj0cfhbft0zthjw", "input": { "text": "Did you ever hear a folk tale about a giant turtle?", "audio": "https://replicate.delivery/pbxt/KpK4hkLwhVAJE9K0DAbZP3YfwLzJyLl09kuPnc4MvCYLcX8m/example_reference.mp3", "speed": 1, "language": "EN_NEWEST" }, "logs": "OpenVoice version: v2\n> Text split to sentences.\nDid you ever hear a folk tale about a giant turtle?\n> ===========================\n 0%| | 0/1 [00:00<?, ?it/s]\n100%|██████████| 1/1 [00:00<00:00, 15.59it/s]", "metrics": { "predict_time": 5.782314, "total_time": 5.844172 }, "output": "https://replicate.delivery/pbxt/3FA9ck5a0woAEJulGzeg3CJkcPVBcLCfdixBNrAxA8ediDrlA/out.wav", "started_at": "2024-05-18T08:43:53.417858Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/1tmwsj9ehhrgj0cfhbft0zthjw", "cancel": "https://api.replicate.com/v1/predictions/1tmwsj9ehhrgj0cfhbft0zthjw/cancel" }, "version": "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d" }
Generated inOpenVoice version: v2 > Text split to sentences. Did you ever hear a folk tale about a giant turtle? > =========================== 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████| 1/1 [00:00<00:00, 15.59it/s]
Want to make some of these yourself?
Run this model