SLNG Text-to-Speech API

Orpheus English

Endpointhttps://api.slng.ai

High-quality streaming TTS with emotion control, hosted on SLNG infrastructure

canopylabs/orpheus:en - websocket

GET

https://api.slng.ai

/v1/tts/slng/canopylabs/orpheus:en

Text-to-Speech API for generating speech from text using SLNG canopylabs/orpheus. High-quality streaming TTS with emotion control, hosted on SLNG infrastructure

WebSocket Endpoint

Establishes a WebSocket connection for real-time text-to-speech.

Connection URL: wss://api.slng.ai/v1/tts/slng/canopylabs/orpheus:en

canopylabs/orpheus:en - websocket › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Upgrade

string · enum · required

Enum values:

websocket

Connection

string · enum · required

Enum values:

Upgrade

X-Region-Override

string · enum

Optional. Specify a target region for this model. If not provided, the system will automatically select an appropriate region.

Enum values:

eu-west

canopylabs/orpheus:en - websocket › Request Body

oneOf

Exactly one variant must match.

Decision Table

Variant	Matching Criteria
	type = object · requires: type, model
	type = object · requires: type, text
	type = object · requires: type
	type = object · requires: type
	type = object · requires: type

Properties for Init Message:

Initialize a session with voice and audio configuration.

type

const · required

Const value: init

model

string · required

Model identifier (e.g., canopylabs/orpheus:en)

voice

string

Voice ID (tara, leah, jess, leo, dan, mia, zac, zoe)

object

Orpheus synthesis configuration

canopylabs/orpheus:en - websocket › Responses

Switching Protocols

oneOf

Exactly one variant must match.

Decision Table

Variant	Matching Criteria
	type = object · requires: type, session_id
	type = object · requires: type, data
	type = object · requires: type, segment_id
	type = object · requires: type, segment_id
	type = object · requires: type
	type = object · requires: type
	type = object · requires: type
	type = object · requires: type, code, message

Properties for Ready Message:

type

const · required

Const value: ready

session_id

string · required

GET/v1/tts/slng/canopylabs/orpheus:en

curl --request GET \
  --url https://api.slng.ai/v1/tts/slng/canopylabs/orpheus:en \
  --header 'Authorization: <string>' \
  --header 'Connection: <string>' \
  --header 'Content-Type: application/json' \
  --header 'Upgrade: <string>' \
  --data '
{
  "type": "init",
  "model": "canopylabs/orpheus:en",
  "voice": "tara",
  "config": {
    "sample_rate": 24000,
    "encoding": "linear16",
    "speed": 1,
    "emotion": "neutral"
  }
}
'

shell

Example Request Body

{
  "type": "init",
  "model": "canopylabs/orpheus:en",
  "voice": "tara",
  "config": {
    "sample_rate": 24000,
    "encoding": "linear16",
    "speed": 1,
    "emotion": "neutral"
  }
}

json

application/json

Example Responses

{
  "type": "ready",
  "session_id": "session_abc123"
}

json

application/json

canopylabs/orpheus:en - http

POST

https://api.slng.ai

/v1/tts/slng/canopylabs/orpheus:en

Text-to-Speech API for generating speech from text using SLNG canopylabs/orpheus. High-quality streaming TTS with emotion control, hosted on SLNG infrastructure

canopylabs/orpheus:en - http › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

X-Region-Override

string · enum

Optional. Specify a target region for this model. If not provided, the system will automatically select an appropriate region.

Enum values:

eu-west

canopylabs/orpheus:en - http › Request Body

prompt

string · minLength: 1

Text to synthesize

text

string · minLength: 1

Text to synthesize (legacy field, use prompt instead)

voice

string · enum

Voice ID

Enum values:

tara

leah

jess

leo

dan

mia

zac

zoe

Default: tara

stream

boolean

Enable streaming response

speed

number · min: 0.5 · max: 2

Speech speed multiplier (0.5-2.0)

emotion

string · enum

Emotion to apply to the speech

Enum values:

neutral

happy

sad

angry

surprised

canopylabs/orpheus:en - http › Responses

Successful synthesis

string · binary

Audio file content

POST/v1/tts/slng/canopylabs/orpheus:en

curl --request POST \
  --url https://api.slng.ai/v1/tts/slng/canopylabs/orpheus:en \
  --header 'Authorization: <string>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "voice": "tara",
  "prompt": "Hello, this is a test of text to speech synthesis."
}
'

shell

Example Request Body

{
  "voice": "tara",
  "prompt": "Hello, this is a test of text to speech synthesis."
}

json

application/json

Example Responses

<binary>

plain

audio/*

Melo v1 Rime Arcana 3 English

canopylabs/orpheus:en - websocket

GET

https://api.slng.ai

/v1/tts/slng/canopylabs/orpheus:en

Text-to-Speech API for generating speech from text using SLNG canopylabs/orpheus. High-quality streaming TTS with emotion control, hosted on SLNG infrastructure

WebSocket Endpoint

Establishes a WebSocket connection for real-time text-to-speech.

Connection URL: wss://api.slng.ai/v1/tts/slng/canopylabs/orpheus:en

canopylabs/orpheus:en - websocket › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Upgrade

string · enum · required

Enum values:

websocket

Connection

string · enum · required

Enum values:

Upgrade

X-Region-Override

string · enum

Optional. Specify a target region for this model. If not provided, the system will automatically select an appropriate region.

Enum values:

eu-west

canopylabs/orpheus:en - websocket › Request Body

oneOf

Exactly one variant must match.

Decision Table

Variant	Matching Criteria
	type = object · requires: type, model
	type = object · requires: type, text
	type = object · requires: type
	type = object · requires: type
	type = object · requires: type

Properties for Init Message:

Initialize a session with voice and audio configuration.

type

const · required

Const value: init

model

string · required

Model identifier (e.g., canopylabs/orpheus:en)

voice

string

Voice ID (tara, leah, jess, leo, dan, mia, zac, zoe)

object

Orpheus synthesis configuration

canopylabs/orpheus:en - websocket › Responses

Switching Protocols

oneOf

Exactly one variant must match.

Decision Table

Variant	Matching Criteria
	type = object · requires: type, session_id
	type = object · requires: type, data
	type = object · requires: type, segment_id
	type = object · requires: type, segment_id
	type = object · requires: type
	type = object · requires: type
	type = object · requires: type
	type = object · requires: type, code, message

Properties for Ready Message:

type

const · required

Const value: ready

session_id

string · required

curl --request GET \ --url https://api.slng.ai/v1/tts/slng/canopylabs/orpheus:en \ --header 'Authorization: <string>' \ --header 'Connection: <string>' \ --header 'Content-Type: application/json' \ --header 'Upgrade: <string>' \ --data ' { "type": "init", "model": "canopylabs/orpheus:en", "voice": "tara", "config": { "sample_rate": 24000, "encoding": "linear16", "speed": 1, "emotion": "neutral" } } '

canopylabs/orpheus:en - http

POST

https://api.slng.ai

/v1/tts/slng/canopylabs/orpheus:en

Text-to-Speech API for generating speech from text using SLNG canopylabs/orpheus. High-quality streaming TTS with emotion control, hosted on SLNG infrastructure

canopylabs/orpheus:en - http › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

X-Region-Override

string · enum

Optional. Specify a target region for this model. If not provided, the system will automatically select an appropriate region.

Enum values:

eu-west

canopylabs/orpheus:en - http › Request Body

prompt

string · minLength: 1

Text to synthesize

text

string · minLength: 1

Text to synthesize (legacy field, use prompt instead)

voice

string · enum

Voice ID

Enum values:

tara

leah

jess

leo

dan

mia

zac

zoe

Default: tara

stream

boolean

Enable streaming response

speed

number · min: 0.5 · max: 2

Speech speed multiplier (0.5-2.0)

emotion

string · enum

Emotion to apply to the speech

Enum values:

neutral

happy

sad

angry

surprised

canopylabs/orpheus:en - http › Responses

Successful synthesis

string · binary

Audio file content