✋ This model is not published yet.
You can claim this model if you're @ben-hayes on GitHub. Contact us.
ben-hayes / neural-waveshaping-synthesis
Efficient neural audio synthesis in the waveform domain
Prediction
ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9ID4jwodgozt5eerjt3kus2svpsxyStatusSucceededSourceWebHardware–Total duration–CreatedInput
- instrument
- Violin
- youtube_url
- https://www.youtube.com/watch?v=dYvPCgcFDIo
- octave_shift
- "1"
- use_fastnewt
- loudness_floor
- "0"
- loudness_scale
- "0.5"
- pitch_smoothing
- "0"
- pitch_conf_filter
- "0"
- loudness_smoothing
- "0"
- loudness_conf_filter
- "0"
- use_full_crepe_model
- youtube_start_in_seconds
- "6.5"
- youtube_length_in_seconds
- "20"
{ "instrument": "Violin", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run ben-hayes/neural-waveshaping-synthesis using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", { input: { instrument: "Violin", youtube_url: "https://www.youtube.com/watch?v=dYvPCgcFDIo", octave_shift: "1", use_fastnewt: false, loudness_floor: "0", loudness_scale: "0.5", pitch_smoothing: "0", pitch_conf_filter: "0", loudness_smoothing: "0", loudness_conf_filter: "0", use_full_crepe_model: true, youtube_start_in_seconds: "6.5", youtube_length_in_seconds: "20" } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun ben-hayes/neural-waveshaping-synthesis using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", input={ "instrument": "Violin", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": False, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": True, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" } ) # The ben-hayes/neural-waveshaping-synthesis model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/ben-hayes/neural-waveshaping-synthesis/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run ben-hayes/neural-waveshaping-synthesis 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": "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", "input": { "instrument": "Violin", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" } }' \ https://api.replicate.com/v1/predictionsTo 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": "2021-08-27T10:02:19.793326Z", "created_at": "2021-08-27T10:01:34.285575Z", "data_removed": false, "error": null, "id": "4jwodgozt5eerjt3kus2svpsxy", "input": { "instrument": "Violin", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" }, "logs": "Downloading youtube video...\nRunning: youtube-dl --format=bestaudio[ext=m4a] --extract-audio --audio-format=wav --output=/tmp/tmpzkoa7w6k/yt_audio.%(ext)s https://www.youtube.com/watch?v=dYvPCgcFDIo\nExtracting F0 with crepe...\nComputing control signals...\nRunning model...\nAudio generated in 0.14 seconds. That's 138.5 times faster than the real time threshold!\nSaving result...", "metrics": { "total_time": 45.507751 }, "output": [ { "file": "https://replicate.delivery/mgxm/0dcc4884-7607-4986-bf1e-4248caeeac9e/out.mp3" } ], "started_at": "2021-12-02T00:30:37.331737Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/4jwodgozt5eerjt3kus2svpsxy", "cancel": "https://api.replicate.com/v1/predictions/4jwodgozt5eerjt3kus2svpsxy/cancel" }, "version": "0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9" }Downloading youtube video... Running: youtube-dl --format=bestaudio[ext=m4a] --extract-audio --audio-format=wav --output=/tmp/tmpzkoa7w6k/yt_audio.%(ext)s https://www.youtube.com/watch?v=dYvPCgcFDIo Extracting F0 with crepe... Computing control signals... Running model... Audio generated in 0.14 seconds. That's 138.5 times faster than the real time threshold! Saving result...Prediction
ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9IDamursmomujbhzlh26s3ovz4ouiStatusSucceededSourceWebHardware–Total duration–CreatedInput
- instrument
- Flute
- youtube_url
- https://www.youtube.com/watch?v=dYvPCgcFDIo
- octave_shift
- "1"
- use_fastnewt
- loudness_floor
- "0"
- loudness_scale
- "0.5"
- pitch_smoothing
- "0"
- pitch_conf_filter
- "0"
- loudness_smoothing
- "0"
- loudness_conf_filter
- "0"
- use_full_crepe_model
- youtube_start_in_seconds
- "6.5"
- youtube_length_in_seconds
- "20"
{ "instrument": "Flute", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run ben-hayes/neural-waveshaping-synthesis using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", { input: { instrument: "Flute", youtube_url: "https://www.youtube.com/watch?v=dYvPCgcFDIo", octave_shift: "1", use_fastnewt: false, loudness_floor: "0", loudness_scale: "0.5", pitch_smoothing: "0", pitch_conf_filter: "0", loudness_smoothing: "0", loudness_conf_filter: "0", use_full_crepe_model: true, youtube_start_in_seconds: "6.5", youtube_length_in_seconds: "20" } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun ben-hayes/neural-waveshaping-synthesis using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", input={ "instrument": "Flute", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": False, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": True, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" } ) # The ben-hayes/neural-waveshaping-synthesis model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/ben-hayes/neural-waveshaping-synthesis/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run ben-hayes/neural-waveshaping-synthesis 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": "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", "input": { "instrument": "Flute", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" } }' \ https://api.replicate.com/v1/predictionsTo 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": "2021-08-27T10:03:52.377784Z", "created_at": "2021-08-27T10:02:52.317522Z", "data_removed": false, "error": null, "id": "amursmomujbhzlh26s3ovz4oui", "input": { "instrument": "Flute", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" }, "logs": "Downloading youtube video...\nRunning: youtube-dl --format=bestaudio[ext=m4a] --extract-audio --audio-format=wav --output=/tmp/tmpeetcr825/yt_audio.%(ext)s https://www.youtube.com/watch?v=dYvPCgcFDIo\nExtracting F0 with crepe...\nComputing control signals...\nRunning model...\nAudio generated in 0.14 seconds. That's 141.8 times faster than the real time threshold!\nSaving result...", "metrics": {}, "output": [ { "file": "https://replicate.delivery/mgxm/9046bcae-3e32-421d-a638-02797043aea2/out.mp3" } ], "started_at": null, "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/amursmomujbhzlh26s3ovz4oui", "cancel": "https://api.replicate.com/v1/predictions/amursmomujbhzlh26s3ovz4oui/cancel" }, "version": "0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9" }Downloading youtube video... Running: youtube-dl --format=bestaudio[ext=m4a] --extract-audio --audio-format=wav --output=/tmp/tmpeetcr825/yt_audio.%(ext)s https://www.youtube.com/watch?v=dYvPCgcFDIo Extracting F0 with crepe... Computing control signals... Running model... Audio generated in 0.14 seconds. That's 141.8 times faster than the real time threshold! Saving result...Prediction
ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9IDyxmcdhxio5hi5iscdp4xjqx7zmStatusSucceededSourceWebHardware–Total duration–CreatedInput
- instrument
- Trumpet
- youtube_url
- https://www.youtube.com/watch?v=dYvPCgcFDIo
- octave_shift
- "1"
- use_fastnewt
- loudness_floor
- "0"
- loudness_scale
- "0.5"
- pitch_smoothing
- "0"
- pitch_conf_filter
- "0"
- loudness_smoothing
- "0"
- loudness_conf_filter
- "0"
- use_full_crepe_model
- youtube_start_in_seconds
- "6.5"
- youtube_length_in_seconds
- "20"
{ "instrument": "Trumpet", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run ben-hayes/neural-waveshaping-synthesis using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", { input: { instrument: "Trumpet", youtube_url: "https://www.youtube.com/watch?v=dYvPCgcFDIo", octave_shift: "1", use_fastnewt: false, loudness_floor: "0", loudness_scale: "0.5", pitch_smoothing: "0", pitch_conf_filter: "0", loudness_smoothing: "0", loudness_conf_filter: "0", use_full_crepe_model: true, youtube_start_in_seconds: "6.5", youtube_length_in_seconds: "20" } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun ben-hayes/neural-waveshaping-synthesis using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", input={ "instrument": "Trumpet", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": False, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": True, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" } ) # The ben-hayes/neural-waveshaping-synthesis model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/ben-hayes/neural-waveshaping-synthesis/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run ben-hayes/neural-waveshaping-synthesis 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": "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", "input": { "instrument": "Trumpet", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" } }' \ https://api.replicate.com/v1/predictionsTo 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": "2021-08-27T10:05:16.044474Z", "created_at": "2021-08-27T10:05:05.473209Z", "data_removed": false, "error": null, "id": "yxmcdhxio5hi5iscdp4xjqx7zm", "input": { "instrument": "Trumpet", "youtube_url": "https://www.youtube.com/watch?v=dYvPCgcFDIo", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true, "youtube_start_in_seconds": "6.5", "youtube_length_in_seconds": "20" }, "logs": "Downloading youtube video...\nRunning: youtube-dl --format=bestaudio[ext=m4a] --extract-audio --audio-format=wav --output=/tmp/tmp4x7my0ao/yt_audio.%(ext)s https://www.youtube.com/watch?v=dYvPCgcFDIo\nExtracting F0 with crepe...\nComputing control signals...\nRunning model...\nAudio generated in 0.14 seconds. That's 141.6 times faster than the real time threshold!\nSaving result...", "metrics": {}, "output": [ { "file": "https://replicate.delivery/mgxm/33e14bbd-0db4-49a0-a4d9-fbc08197a579/out.mp3" } ], "started_at": null, "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/yxmcdhxio5hi5iscdp4xjqx7zm", "cancel": "https://api.replicate.com/v1/predictions/yxmcdhxio5hi5iscdp4xjqx7zm/cancel" }, "version": "0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9" }Downloading youtube video... Running: youtube-dl --format=bestaudio[ext=m4a] --extract-audio --audio-format=wav --output=/tmp/tmp4x7my0ao/yt_audio.%(ext)s https://www.youtube.com/watch?v=dYvPCgcFDIo Extracting F0 with crepe... Computing control signals... Running model... Audio generated in 0.14 seconds. That's 141.6 times faster than the real time threshold! Saving result...Prediction
ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9IDfxylcy4g4rdjvogw476hcwkasmStatusSucceededSourceWebHardware–Total duration–CreatedInput
- audio_file
- 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.
- instrument
- Violin
- octave_shift
- "1"
- use_fastnewt
- loudness_floor
- "0"
- loudness_scale
- "0.5"
- pitch_smoothing
- "0"
- pitch_conf_filter
- "0"
- loudness_smoothing
- "0"
- loudness_conf_filter
- "0"
- use_full_crepe_model
{ "audio_file": "https://replicate.delivery/mgxm/b97b491a-4858-4a19-88c3-b3a05cf0a375/polska.mp3", "instrument": "Violin", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run ben-hayes/neural-waveshaping-synthesis using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", { input: { audio_file: "https://replicate.delivery/mgxm/b97b491a-4858-4a19-88c3-b3a05cf0a375/polska.mp3", instrument: "Violin", octave_shift: "1", use_fastnewt: false, loudness_floor: "0", loudness_scale: "0.5", pitch_smoothing: "0", pitch_conf_filter: "0", loudness_smoothing: "0", loudness_conf_filter: "0", use_full_crepe_model: true } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun ben-hayes/neural-waveshaping-synthesis using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", input={ "audio_file": "https://replicate.delivery/mgxm/b97b491a-4858-4a19-88c3-b3a05cf0a375/polska.mp3", "instrument": "Violin", "octave_shift": "1", "use_fastnewt": False, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": True } ) # The ben-hayes/neural-waveshaping-synthesis model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/ben-hayes/neural-waveshaping-synthesis/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run ben-hayes/neural-waveshaping-synthesis 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": "ben-hayes/neural-waveshaping-synthesis:0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9", "input": { "audio_file": "https://replicate.delivery/mgxm/b97b491a-4858-4a19-88c3-b3a05cf0a375/polska.mp3", "instrument": "Violin", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true } }' \ https://api.replicate.com/v1/predictionsTo 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": "2021-08-27T10:11:37.561817Z", "created_at": "2021-08-27T10:11:28.626252Z", "data_removed": false, "error": null, "id": "fxylcy4g4rdjvogw476hcwkasm", "input": { "audio_file": "https://replicate.delivery/mgxm/b97b491a-4858-4a19-88c3-b3a05cf0a375/polska.mp3", "instrument": "Violin", "octave_shift": "1", "use_fastnewt": false, "loudness_floor": "0", "loudness_scale": "0.5", "pitch_smoothing": "0", "pitch_conf_filter": "0", "loudness_smoothing": "0", "loudness_conf_filter": "0", "use_full_crepe_model": true }, "logs": "Reading input file...\nExtracting F0 with crepe...\nComputing control signals...\nRunning model...\nAudio generated in 0.14 seconds. That's 138.8 times faster than the real time threshold!\nSaving result...", "metrics": {}, "output": [ { "file": "https://replicate.delivery/mgxm/f9f427c6-b382-4c4f-9b93-df4819a329db/out.mp3" } ], "started_at": null, "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/fxylcy4g4rdjvogw476hcwkasm", "cancel": "https://api.replicate.com/v1/predictions/fxylcy4g4rdjvogw476hcwkasm/cancel" }, "version": "0d8b1d7be262c95cde0b35bf15112d0faa43a3b456dd5bde0cc7ecc26ba7d0a9" }Reading input file... Extracting F0 with crepe... Computing control signals... Running model... Audio generated in 0.14 seconds. That's 138.8 times faster than the real time threshold! Saving result...
Want to make some of these yourself?
Run this model