lucataco
/
orpheus-3b-0.1-ft
Orpheus 3B - high quality, emotive Text to Speech
Prediction
lucataco/orpheus-3b-0.1-ft:79f2a473Input
- text
- Hey there my name is Tara, <chuckle> and I'm a speech generation model that can sound like a person.
- top_p
- 0.95
- voice
- tara
- temperature
- 0.6
- max_new_tokens
- 1200
- repetition_penalty
- 1.1
{ "text": "Hey there my name is Tara, <chuckle> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", { input: { text: "Hey there my name is Tara, <chuckle> and I'm a speech generation model that can sound like a person.", top_p: 0.95, voice: "tara", temperature: 0.6, max_new_tokens: 1200, repetition_penalty: 1.1 } } ); 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 replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", input={ "text": "Hey there my name is Tara, <chuckle> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/orpheus-3b-0.1-ft 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": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", "input": { "text": "Hey there my name is Tara, <chuckle> and I\'m a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f \ -i $'text="Hey there my name is Tara, <chuckle> and I\'m a speech generation model that can sound like a person."' \ -i 'top_p=0.95' \ -i 'voice="tara"' \ -i 'temperature=0.6' \ -i 'max_new_tokens=1200' \ -i 'repetition_penalty=1.1'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207fcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "text": "Hey there my name is Tara, <chuckle> and I\'m a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
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.
The media could not be loaded, either because the server or network failed or because the format is not supported.Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2025-03-20T17:39:28.112769Z", "created_at": "2025-03-20T17:39:18.542000Z", "data_removed": false, "error": null, "id": "2zmckjaqhsrme0cnpjhtb44ar8", "input": { "text": "Hey there my name is Tara, <chuckle> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }, "logs": "Setting `pad_token_id` to `eos_token_id`:128258 for open-end generation.", "metrics": { "predict_time": 9.564411705, "total_time": 9.570769 }, "output": "https://replicate.delivery/xezq/KtEzfMb9r027R6i3dImgifxrZn4X3m42Ew5KMGmHRpdQTgaUA/output.wav", "started_at": "2025-03-20T17:39:18.548357Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-rbxe63cyje5ealpnygxwfhxu752ttsjlyfevmrbxfn7lanm5qhcq", "get": "https://api.replicate.com/v1/predictions/2zmckjaqhsrme0cnpjhtb44ar8", "cancel": "https://api.replicate.com/v1/predictions/2zmckjaqhsrme0cnpjhtb44ar8/cancel" }, "version": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f" }Generated inSetting `pad_token_id` to `eos_token_id`:128258 for open-end generation.Prediction
lucataco/orpheus-3b-0.1-ft:79f2a473IDkgsp499j3nrma0cnpjjbh4t2wcStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- text
- I've also been taught to understand and produce paralinguistic things like sighing, or chuckling, or yawning!
- top_p
- 0.95
- voice
- dan
- temperature
- 0.6
- max_new_tokens
- 1200
- repetition_penalty
- 1.1
{ "text": "I've also been taught to understand and produce paralinguistic things like sighing, or chuckling, or yawning!", "top_p": 0.95, "voice": "dan", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", { input: { text: "I've also been taught to understand and produce paralinguistic things like sighing, or chuckling, or yawning!", top_p: 0.95, voice: "dan", temperature: 0.6, max_new_tokens: 1200, repetition_penalty: 1.1 } } ); 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 replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", input={ "text": "I've also been taught to understand and produce paralinguistic things like sighing, or chuckling, or yawning!", "top_p": 0.95, "voice": "dan", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/orpheus-3b-0.1-ft 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": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", "input": { "text": "I\'ve also been taught to understand and produce paralinguistic things like sighing, or chuckling, or yawning!", "top_p": 0.95, "voice": "dan", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f \ -i $'text="I\'ve also been taught to understand and produce paralinguistic things like sighing, or chuckling, or yawning!"' \ -i 'top_p=0.95' \ -i 'voice="dan"' \ -i 'temperature=0.6' \ -i 'max_new_tokens=1200' \ -i 'repetition_penalty=1.1'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207fcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "text": "I\'ve also been taught to understand and produce paralinguistic things like sighing, or chuckling, or yawning!", "top_p": 0.95, "voice": "dan", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
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.
The media could not be loaded, either because the server or network failed or because the format is not supported.Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2025-03-20T17:40:25.520354Z", "created_at": "2025-03-20T17:40:14.493000Z", "data_removed": false, "error": null, "id": "kgsp499j3nrma0cnpjjbh4t2wc", "input": { "text": "I've also been taught to understand and produce paralinguistic things like sighing, or chuckling, or yawning!", "top_p": 0.95, "voice": "dan", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }, "logs": "Setting `pad_token_id` to `eos_token_id`:128258 for open-end generation.", "metrics": { "predict_time": 11.021412287, "total_time": 11.027354 }, "output": "https://replicate.delivery/xezq/cVPBTsvQsSaCFthZWEd8OaONX5ZKvkzqlmnrr6c3eDeJUgaUA/output.wav", "started_at": "2025-03-20T17:40:14.498942Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-lyuhxqxefk7bjg7274hmsvgl7cx473dygnmscmka43ouqosrzcaa", "get": "https://api.replicate.com/v1/predictions/kgsp499j3nrma0cnpjjbh4t2wc", "cancel": "https://api.replicate.com/v1/predictions/kgsp499j3nrma0cnpjjbh4t2wc/cancel" }, "version": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f" }Generated inSetting `pad_token_id` to `eos_token_id`:128258 for open-end generation.Prediction
lucataco/orpheus-3b-0.1-ft:79f2a473ID6m8n79f31hrmc0cnpjj9tqy4d0StatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- text
- I live in San Francisco, and have, uhm let's see, 3 billion 7 hundred ... well, lets just say a lot of parameters.
- top_p
- 0.95
- voice
- emma
- temperature
- 0.6
- max_new_tokens
- 1200
- repetition_penalty
- 1.1
{ "text": "I live in San Francisco, and have, uhm let's see, 3 billion 7 hundred ... well, lets just say a lot of parameters.", "top_p": 0.95, "voice": "emma", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", { input: { text: "I live in San Francisco, and have, uhm let's see, 3 billion 7 hundred ... well, lets just say a lot of parameters.", top_p: 0.95, voice: "emma", temperature: 0.6, max_new_tokens: 1200, repetition_penalty: 1.1 } } ); 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 replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", input={ "text": "I live in San Francisco, and have, uhm let's see, 3 billion 7 hundred ... well, lets just say a lot of parameters.", "top_p": 0.95, "voice": "emma", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/orpheus-3b-0.1-ft 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": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", "input": { "text": "I live in San Francisco, and have, uhm let\'s see, 3 billion 7 hundred ... well, lets just say a lot of parameters.", "top_p": 0.95, "voice": "emma", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f \ -i $'text="I live in San Francisco, and have, uhm let\'s see, 3 billion 7 hundred ... well, lets just say a lot of parameters."' \ -i 'top_p=0.95' \ -i 'voice="emma"' \ -i 'temperature=0.6' \ -i 'max_new_tokens=1200' \ -i 'repetition_penalty=1.1'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207fcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "text": "I live in San Francisco, and have, uhm let\'s see, 3 billion 7 hundred ... well, lets just say a lot of parameters.", "top_p": 0.95, "voice": "emma", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
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.
The media could not be loaded, either because the server or network failed or because the format is not supported.Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2025-03-20T17:41:10.329315Z", "created_at": "2025-03-20T17:40:59.788000Z", "data_removed": false, "error": null, "id": "6m8n79f31hrmc0cnpjj9tqy4d0", "input": { "text": "I live in San Francisco, and have, uhm let's see, 3 billion 7 hundred ... well, lets just say a lot of parameters.", "top_p": 0.95, "voice": "emma", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }, "logs": "Setting `pad_token_id` to `eos_token_id`:128258 for open-end generation.", "metrics": { "predict_time": 10.535885434, "total_time": 10.541315 }, "output": "https://replicate.delivery/xezq/Pz8SSpObwKq2CViGbBMhWuYDJgWqFvdKvppZfYJxhcLbKQNKA/output.wav", "started_at": "2025-03-20T17:40:59.793429Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-bl77fh7yclly5f5i3bcz637myaseygcc253aofwxqkb2h6zpguoa", "get": "https://api.replicate.com/v1/predictions/6m8n79f31hrmc0cnpjj9tqy4d0", "cancel": "https://api.replicate.com/v1/predictions/6m8n79f31hrmc0cnpjj9tqy4d0/cancel" }, "version": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f" }Generated inSetting `pad_token_id` to `eos_token_id`:128258 for open-end generation.Prediction
lucataco/orpheus-3b-0.1-ft:79f2a473IDcdkhczh719rm80cnpnp9cpdvgrStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- text
- Hey there my name is Tara, <laugh> and I'm a speech generation model that can sound like a person.
- top_p
- 0.95
- voice
- tara
- temperature
- 0.6
- max_new_tokens
- 1200
- repetition_penalty
- 1.1
{ "text": "Hey there my name is Tara, <laugh> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", { input: { text: "Hey there my name is Tara, <laugh> and I'm a speech generation model that can sound like a person.", top_p: 0.95, voice: "tara", temperature: 0.6, max_new_tokens: 1200, repetition_penalty: 1.1 } } ); 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 replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", input={ "text": "Hey there my name is Tara, <laugh> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/orpheus-3b-0.1-ft 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": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", "input": { "text": "Hey there my name is Tara, <laugh> and I\'m a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f \ -i $'text="Hey there my name is Tara, <laugh> and I\'m a speech generation model that can sound like a person."' \ -i 'top_p=0.95' \ -i 'voice="tara"' \ -i 'temperature=0.6' \ -i 'max_new_tokens=1200' \ -i 'repetition_penalty=1.1'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207fcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "text": "Hey there my name is Tara, <laugh> and I\'m a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
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.
The media could not be loaded, either because the server or network failed or because the format is not supported.Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2025-03-20T21:18:47.027731Z", "created_at": "2025-03-20T21:18:38.858000Z", "data_removed": false, "error": null, "id": "cdkhczh719rm80cnpnp9cpdvgr", "input": { "text": "Hey there my name is Tara, <laugh> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }, "logs": "Setting `pad_token_id` to `eos_token_id`:128258 for open-end generation.", "metrics": { "predict_time": 8.162548887, "total_time": 8.169731 }, "output": "https://replicate.delivery/xezq/5tZXdxJyrwbPL9x6GaaFGwXGeJIStx2elVPEJ6wvDyfvBH1oA/output.wav", "started_at": "2025-03-20T21:18:38.865182Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-mb64zioxa23anzhqelttts4nw3cbgksuoqxgcy2newdiyk5ddyuq", "get": "https://api.replicate.com/v1/predictions/cdkhczh719rm80cnpnp9cpdvgr", "cancel": "https://api.replicate.com/v1/predictions/cdkhczh719rm80cnpnp9cpdvgr/cancel" }, "version": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f" }Generated inSetting `pad_token_id` to `eos_token_id`:128258 for open-end generation.Prediction
lucataco/orpheus-3b-0.1-ft:79f2a473ID6ck4fdq87drmc0cnpnp8tj5264StatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- text
- Hey there my name is Tara, <sigh> and I'm a speech generation model that can sound like a person.
- top_p
- 0.95
- voice
- tara
- temperature
- 0.6
- max_new_tokens
- 1200
- repetition_penalty
- 1.1
{ "text": "Hey there my name is Tara, <sigh> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", { input: { text: "Hey there my name is Tara, <sigh> and I'm a speech generation model that can sound like a person.", top_p: 0.95, voice: "tara", temperature: 0.6, max_new_tokens: 1200, repetition_penalty: 1.1 } } ); 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 replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", input={ "text": "Hey there my name is Tara, <sigh> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/orpheus-3b-0.1-ft 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": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", "input": { "text": "Hey there my name is Tara, <sigh> and I\'m a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f \ -i $'text="Hey there my name is Tara, <sigh> and I\'m a speech generation model that can sound like a person."' \ -i 'top_p=0.95' \ -i 'voice="tara"' \ -i 'temperature=0.6' \ -i 'max_new_tokens=1200' \ -i 'repetition_penalty=1.1'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207fcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "text": "Hey there my name is Tara, <sigh> and I\'m a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
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.
The media could not be loaded, either because the server or network failed or because the format is not supported.Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2025-03-20T21:19:37.638608Z", "created_at": "2025-03-20T21:19:28.315000Z", "data_removed": false, "error": null, "id": "6ck4fdq87drmc0cnpnp8tj5264", "input": { "text": "Hey there my name is Tara, <sigh> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }, "logs": "Setting `pad_token_id` to `eos_token_id`:128258 for open-end generation.", "metrics": { "predict_time": 9.315479797, "total_time": 9.323608 }, "output": "https://replicate.delivery/xezq/qtdhOOJjqvqgE5ijkFtQa356HqGoe9piKr3NRCON1as0wRNKA/output.wav", "started_at": "2025-03-20T21:19:28.323129Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-umqgztulrnyf3p4kxhwxv5ghedld2rutqzrdayu5s2ayzb2lr4iq", "get": "https://api.replicate.com/v1/predictions/6ck4fdq87drmc0cnpnp8tj5264", "cancel": "https://api.replicate.com/v1/predictions/6ck4fdq87drmc0cnpnp8tj5264/cancel" }, "version": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f" }Generated inSetting `pad_token_id` to `eos_token_id`:128258 for open-end generation.Prediction
lucataco/orpheus-3b-0.1-ft:79f2a473IDbtdjj9axkhrme0cnpnpswdag9cStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- text
- Hey there my name is Tara, <gasp> and I'm a speech generation model that can sound like a person.
- top_p
- 0.95
- voice
- tara
- temperature
- 0.6
- max_new_tokens
- 1200
- repetition_penalty
- 1.1
{ "text": "Hey there my name is Tara, <gasp> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", { input: { text: "Hey there my name is Tara, <gasp> and I'm a speech generation model that can sound like a person.", top_p: 0.95, voice: "tara", temperature: 0.6, max_new_tokens: 1200, repetition_penalty: 1.1 } } ); 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 replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun lucataco/orpheus-3b-0.1-ft using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/orpheus-3b-0.1-ft:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", input={ "text": "Hey there my name is Tara, <gasp> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/orpheus-3b-0.1-ft 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": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f", "input": { "text": "Hey there my name is Tara, <gasp> and I\'m a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f \ -i $'text="Hey there my name is Tara, <gasp> and I\'m a speech generation model that can sound like a person."' \ -i 'top_p=0.95' \ -i 'voice="tara"' \ -i 'temperature=0.6' \ -i 'max_new_tokens=1200' \ -i 'repetition_penalty=1.1'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/orpheus-3b-0.1-ft@sha256:79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207fcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "text": "Hey there my name is Tara, <gasp> and I\'m a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
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.
The media could not be loaded, either because the server or network failed or because the format is not supported.Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{ "completed_at": "2025-03-20T21:20:05.894851Z", "created_at": "2025-03-20T21:19:58.364000Z", "data_removed": false, "error": null, "id": "btdjj9axkhrme0cnpnpswdag9c", "input": { "text": "Hey there my name is Tara, <gasp> and I'm a speech generation model that can sound like a person.", "top_p": 0.95, "voice": "tara", "temperature": 0.6, "max_new_tokens": 1200, "repetition_penalty": 1.1 }, "logs": "Setting `pad_token_id` to `eos_token_id`:128258 for open-end generation.", "metrics": { "predict_time": 7.523227767, "total_time": 7.530851 }, "output": "https://replicate.delivery/xezq/q18z8ID195I0MpWLSWn62VDvuIGOtCsdKR7ceMzCWwkCxRNKA/output.wav", "started_at": "2025-03-20T21:19:58.371623Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-d5pnjgksbn4on3sf2flppjww6azqvsjhsodnesauvyuswybtndvq", "get": "https://api.replicate.com/v1/predictions/btdjj9axkhrme0cnpnpswdag9c", "cancel": "https://api.replicate.com/v1/predictions/btdjj9axkhrme0cnpnpswdag9c/cancel" }, "version": "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f" }Generated inSetting `pad_token_id` to `eos_token_id`:128258 for open-end generation.
Want to make some of these yourself?
Run this model