ttsds
/
amphion_naturalspeech2
The NaturalSpeech2 model by Amphion.
Prediction
ttsds/amphion_naturalspeech2:ef5a325879add6bf5f161568d9ebad53824fa3b6b7f0eacb7f300e8720e861f7IDh59w8jg1hhrm80cmjg48wv72s8StatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- text
- With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.
- speaker_reference
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%00:00:000Stream 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.
{ "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.", "speaker_reference": "https://replicate.delivery/pbxt/MN9oVKrayGMTWkp7zLYiFI4f2MxcvUNXdLPZKNm2XF6pfFCd/example.wav" }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run ttsds/amphion_naturalspeech2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ttsds/amphion_naturalspeech2:ef5a325879add6bf5f161568d9ebad53824fa3b6b7f0eacb7f300e8720e861f7", { input: { text: "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.", speaker_reference: "https://replicate.delivery/pbxt/MN9oVKrayGMTWkp7zLYiFI4f2MxcvUNXdLPZKNm2XF6pfFCd/example.wav" } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run ttsds/amphion_naturalspeech2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ttsds/amphion_naturalspeech2:ef5a325879add6bf5f161568d9ebad53824fa3b6b7f0eacb7f300e8720e861f7", input={ "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.", "speaker_reference": "https://replicate.delivery/pbxt/MN9oVKrayGMTWkp7zLYiFI4f2MxcvUNXdLPZKNm2XF6pfFCd/example.wav" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run ttsds/amphion_naturalspeech2 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": "ef5a325879add6bf5f161568d9ebad53824fa3b6b7f0eacb7f300e8720e861f7", "input": { "text": "With tenure, Suzie\'d have all the more leisure for yachting, but her publications are no good.", "speaker_reference": "https://replicate.delivery/pbxt/MN9oVKrayGMTWkp7zLYiFI4f2MxcvUNXdLPZKNm2XF6pfFCd/example.wav" } }' \ 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%00:00:000Stream 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": "2025-01-23T16:40:32.079267Z", "created_at": "2025-01-23T16:39:00.236000Z", "data_removed": false, "error": null, "id": "h59w8jg1hhrm80cmjg48wv72s8", "input": { "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.", "speaker_reference": "https://replicate.delivery/pbxt/MN9oVKrayGMTWkp7zLYiFI4f2MxcvUNXdLPZKNm2XF6pfFCd/example.wav" }, "logs": "W IH0 DH T EH1 N Y ER0 sp S UW1 Z IY0 D HH AE1 V AO1 L DH AH0 M AO1 R L EH1 ZH ER0 F AO1 R Y AA1 T IH0 NG sp B AH1 T HH ER0 P AH2 B L IH0 K EY1 SH AH0 N Z AA1 R N OW1 G IH0 D\ntensor([[80, 44, 27, 69, 30, 55, 81, 33, 84, 67, 77, 82, 48, 26, 42, 6, 79, 14,\n53, 27, 9, 54, 14, 66, 53, 30, 83, 33, 40, 14, 66, 81, 2, 69, 44, 56,\n84, 24, 10, 69, 42, 33, 65, 11, 24, 53, 44, 52, 38, 68, 9, 55, 82, 2,\n66, 55, 59, 41, 44, 26]], device='cuda:0')\ntensor([[ 3.9186, 2.9686, 4.9976, 5.7980, 4.0413, 3.9953, 3.9211, 3.9709,\n5.0094, 10.3756, 8.8338, 5.9407, 4.8495, 3.8872, 0.9731, 6.5990,\n5.0840, 8.3756, 5.0295, 4.0766, 2.9993, 6.2080, 5.3888, 5.3165,\n5.1823, 6.1473, 6.7604, 7.5368, 8.0171, 2.1517, 3.9014, 7.5853,\n9.0661, 4.1307, 4.0265, 5.0240, 5.1804, 5.9589, 4.9108, 3.0568,\n0.9921, 5.6249, 7.6311, 4.8512, 3.9711, 2.0713, 3.0145, 7.2740,\n7.4062, 7.9518, 3.0312, 3.8800, 3.9691, 4.0073, 3.0389, 6.5661,\n9.4134, 4.9636, 5.0012, 6.6313]], device='cuda:0')\ntensor([[ 4, 3, 5, 6, 4, 4, 4, 4, 5, 10, 9, 6, 5, 4, 1, 7, 5, 8,\n5, 4, 3, 6, 5, 5, 5, 6, 7, 8, 8, 2, 4, 8, 9, 4, 4, 5,\n5, 6, 5, 3, 1, 6, 8, 5, 4, 2, 3, 7, 7, 8, 3, 4, 4, 4,\n3, 7, 9, 5, 5, 7]], device='cuda:0')\ntensor(313, device='cuda:0')", "metrics": { "predict_time": 3.531545554, "total_time": 91.843267 }, "output": "https://replicate.delivery/xezq/q8K8D4KGk2qyLtauPVaoeAdU04GQe6E9ccMAo6LszblAMCIUA/output.wav", "started_at": "2025-01-23T16:40:28.547721Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-taze72rdmg6lebiaq7czkmj2tc4mmcrpbtu4fld54tyrmilkyy7a", "get": "https://api.replicate.com/v1/predictions/h59w8jg1hhrm80cmjg48wv72s8", "cancel": "https://api.replicate.com/v1/predictions/h59w8jg1hhrm80cmjg48wv72s8/cancel" }, "version": "ef5a325879add6bf5f161568d9ebad53824fa3b6b7f0eacb7f300e8720e861f7" }
Generated inW IH0 DH T EH1 N Y ER0 sp S UW1 Z IY0 D HH AE1 V AO1 L DH AH0 M AO1 R L EH1 ZH ER0 F AO1 R Y AA1 T IH0 NG sp B AH1 T HH ER0 P AH2 B L IH0 K EY1 SH AH0 N Z AA1 R N OW1 G IH0 D tensor([[80, 44, 27, 69, 30, 55, 81, 33, 84, 67, 77, 82, 48, 26, 42, 6, 79, 14, 53, 27, 9, 54, 14, 66, 53, 30, 83, 33, 40, 14, 66, 81, 2, 69, 44, 56, 84, 24, 10, 69, 42, 33, 65, 11, 24, 53, 44, 52, 38, 68, 9, 55, 82, 2, 66, 55, 59, 41, 44, 26]], device='cuda:0') tensor([[ 3.9186, 2.9686, 4.9976, 5.7980, 4.0413, 3.9953, 3.9211, 3.9709, 5.0094, 10.3756, 8.8338, 5.9407, 4.8495, 3.8872, 0.9731, 6.5990, 5.0840, 8.3756, 5.0295, 4.0766, 2.9993, 6.2080, 5.3888, 5.3165, 5.1823, 6.1473, 6.7604, 7.5368, 8.0171, 2.1517, 3.9014, 7.5853, 9.0661, 4.1307, 4.0265, 5.0240, 5.1804, 5.9589, 4.9108, 3.0568, 0.9921, 5.6249, 7.6311, 4.8512, 3.9711, 2.0713, 3.0145, 7.2740, 7.4062, 7.9518, 3.0312, 3.8800, 3.9691, 4.0073, 3.0389, 6.5661, 9.4134, 4.9636, 5.0012, 6.6313]], device='cuda:0') tensor([[ 4, 3, 5, 6, 4, 4, 4, 4, 5, 10, 9, 6, 5, 4, 1, 7, 5, 8, 5, 4, 3, 6, 5, 5, 5, 6, 7, 8, 8, 2, 4, 8, 9, 4, 4, 5, 5, 6, 5, 3, 1, 6, 8, 5, 4, 2, 3, 7, 7, 8, 3, 4, 4, 4, 3, 7, 9, 5, 5, 7]], device='cuda:0') tensor(313, device='cuda:0')
Prediction
ttsds/amphion_naturalspeech2:0abd96869052331425d3398e42335eef5ad20d5f264a98fd894be08a77c3eda6IDkeranpt5shrge0cmjfpbqxf4qwStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- text
- With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.
- speaker_reference
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%00:00:000Stream 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.
{ "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.", "speaker_reference": "https://replicate.delivery/pbxt/MN9oVKrayGMTWkp7zLYiFI4f2MxcvUNXdLPZKNm2XF6pfFCd/example.wav" }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run ttsds/amphion_naturalspeech2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ttsds/amphion_naturalspeech2:0abd96869052331425d3398e42335eef5ad20d5f264a98fd894be08a77c3eda6", { input: { text: "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.", speaker_reference: "https://replicate.delivery/pbxt/MN9oVKrayGMTWkp7zLYiFI4f2MxcvUNXdLPZKNm2XF6pfFCd/example.wav" } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run ttsds/amphion_naturalspeech2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ttsds/amphion_naturalspeech2:0abd96869052331425d3398e42335eef5ad20d5f264a98fd894be08a77c3eda6", input={ "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.", "speaker_reference": "https://replicate.delivery/pbxt/MN9oVKrayGMTWkp7zLYiFI4f2MxcvUNXdLPZKNm2XF6pfFCd/example.wav" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run ttsds/amphion_naturalspeech2 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": "0abd96869052331425d3398e42335eef5ad20d5f264a98fd894be08a77c3eda6", "input": { "text": "With tenure, Suzie\'d have all the more leisure for yachting, but her publications are no good.", "speaker_reference": "https://replicate.delivery/pbxt/MN9oVKrayGMTWkp7zLYiFI4f2MxcvUNXdLPZKNm2XF6pfFCd/example.wav" } }' \ 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%00:00:000Stream 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": "2025-01-23T16:12:59.387179Z", "created_at": "2025-01-23T16:08:42.700000Z", "data_removed": false, "error": null, "id": "keranpt5shrge0cmjfpbqxf4qw", "input": { "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.", "speaker_reference": "https://replicate.delivery/pbxt/MN9oVKrayGMTWkp7zLYiFI4f2MxcvUNXdLPZKNm2XF6pfFCd/example.wav" }, "logs": "W IH0 DH T EH1 N Y ER0 sp S UW1 Z IY0 D HH AE1 V AO1 L DH AH0 M AO1 R L EH1 ZH ER0 F AO1 R Y AA1 T IH0 NG sp B AH1 T HH ER0 P AH2 B L IH0 K EY1 SH AH0 N Z AA1 R N OW1 G IH0 D\ntensor([[80, 44, 27, 69, 30, 55, 81, 33, 84, 67, 77, 82, 48, 26, 42, 6, 79, 14,\n53, 27, 9, 54, 14, 66, 53, 30, 83, 33, 40, 14, 66, 81, 2, 69, 44, 56,\n84, 24, 10, 69, 42, 33, 65, 11, 24, 53, 44, 52, 38, 68, 9, 55, 82, 2,\n66, 55, 59, 41, 44, 26]])\ntensor([[ 3.8367, 2.9391, 4.0850, 5.9560, 4.1298, 4.0695, 3.1016, 4.7869,\n4.7237, 10.3392, 7.3706, 6.1499, 4.7396, 5.0457, 0.9803, 7.5274,\n4.9264, 9.0658, 3.9305, 4.0305, 3.0307, 6.1794, 6.1317, 4.0176,\n5.0900, 5.2507, 6.7618, 7.7431, 7.7983, 2.0229, 3.0184, 6.4749,\n8.4156, 3.9431, 5.2211, 5.5814, 4.8076, 4.9003, 3.9075, 3.1413,\n0.9722, 5.8797, 7.5846, 5.0244, 3.9884, 2.0524, 3.0200, 7.0095,\n7.7940, 8.1469, 2.9959, 4.6731, 4.0029, 3.0495, 2.9745, 6.7565,\n10.1403, 5.1554, 5.2518, 6.8350]])\ntensor([[ 4, 3, 4, 6, 4, 4, 3, 5, 5, 10, 7, 6, 5, 5, 1, 8, 5, 9,\n4, 4, 3, 6, 6, 4, 5, 5, 7, 8, 8, 2, 3, 6, 8, 4, 5, 6,\n5, 5, 4, 3, 1, 6, 8, 5, 4, 2, 3, 7, 8, 8, 3, 5, 4, 3,\n3, 7, 10, 5, 5, 7]])\ntensor(309)", "metrics": { "predict_time": 195.651276946, "total_time": 256.687179 }, "output": "https://replicate.delivery/czjl/YES9uzR9fKU2bCMenbHApkZWlqmvjWHm7fuppjloj95WkDQoA/output.wav", "started_at": "2025-01-23T16:09:43.735902Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/fddq-3tbk7kxsogm7jbjpuyqqxqsjtbkmjgvxdkl734ngczerkfghrw4a", "get": "https://api.replicate.com/v1/predictions/keranpt5shrge0cmjfpbqxf4qw", "cancel": "https://api.replicate.com/v1/predictions/keranpt5shrge0cmjfpbqxf4qw/cancel" }, "version": "0abd96869052331425d3398e42335eef5ad20d5f264a98fd894be08a77c3eda6" }
Generated inW IH0 DH T EH1 N Y ER0 sp S UW1 Z IY0 D HH AE1 V AO1 L DH AH0 M AO1 R L EH1 ZH ER0 F AO1 R Y AA1 T IH0 NG sp B AH1 T HH ER0 P AH2 B L IH0 K EY1 SH AH0 N Z AA1 R N OW1 G IH0 D tensor([[80, 44, 27, 69, 30, 55, 81, 33, 84, 67, 77, 82, 48, 26, 42, 6, 79, 14, 53, 27, 9, 54, 14, 66, 53, 30, 83, 33, 40, 14, 66, 81, 2, 69, 44, 56, 84, 24, 10, 69, 42, 33, 65, 11, 24, 53, 44, 52, 38, 68, 9, 55, 82, 2, 66, 55, 59, 41, 44, 26]]) tensor([[ 3.8367, 2.9391, 4.0850, 5.9560, 4.1298, 4.0695, 3.1016, 4.7869, 4.7237, 10.3392, 7.3706, 6.1499, 4.7396, 5.0457, 0.9803, 7.5274, 4.9264, 9.0658, 3.9305, 4.0305, 3.0307, 6.1794, 6.1317, 4.0176, 5.0900, 5.2507, 6.7618, 7.7431, 7.7983, 2.0229, 3.0184, 6.4749, 8.4156, 3.9431, 5.2211, 5.5814, 4.8076, 4.9003, 3.9075, 3.1413, 0.9722, 5.8797, 7.5846, 5.0244, 3.9884, 2.0524, 3.0200, 7.0095, 7.7940, 8.1469, 2.9959, 4.6731, 4.0029, 3.0495, 2.9745, 6.7565, 10.1403, 5.1554, 5.2518, 6.8350]]) tensor([[ 4, 3, 4, 6, 4, 4, 3, 5, 5, 10, 7, 6, 5, 5, 1, 8, 5, 9, 4, 4, 3, 6, 6, 4, 5, 5, 7, 8, 8, 2, 3, 6, 8, 4, 5, 6, 5, 5, 4, 3, 1, 6, 8, 5, 4, 2, 3, 7, 8, 8, 3, 5, 4, 3, 3, 7, 10, 5, 5, 7]]) tensor(309)
Want to make some of these yourself?
Run this model