3B Orpheus TTS (0.1) Serverless API

Orpheus TTS is an open-source text-to-speech (TTS) system powered by the Llama 3B language model, designed for high-quality and customizable speech synthesis.

~117.52s

~$0.124

Playground API

Pricing

~117.52s

~$0.124

 1import requests
 2import json
 3
 4url = "https://api.segmind.com/v1/orpheus-3b-0.1"
 5headers = {
 6    "x-api-key": "YOUR_API_KEY",
 7    "Content-Type": "application/json"
 8}
 9
10data = {
11    "text": "Today has been... exhausting. <sigh> First, I missed the bus. Then it started pouring rain—of course, I forgot my umbrella. <groan> And just when I thought things couldn’t get worse, I spilled coffee all over my white shirt right before the presentation. <cough> But hey, at least I survived... kind of.",
12    "top_p": 0.95,
13    "voice": "dan",
14    "temperature": 0.6,
15    "max_new_tokens": 1200,
16    "repetition_penalty": 1.1
17}
18
19response = requests.post(url, headers=headers, json=data)
20
21if response.status_code == 200:
22    result = response.json()
23    print(json.dumps(result, indent=2))
24else:
25    print(f"Error: {response.status_code}")
26    print(response.text)

 1import requests
 2import json
 3
 4url = "https://api.segmind.com/v1/orpheus-3b-0.1"
 5headers = {
 6    "x-api-key": "YOUR_API_KEY",
 7    "Content-Type": "application/json"
 8}
 9
10data = {
11    "text": "Today has been... exhausting. <sigh> First, I missed the bus. Then it started pouring rain—of course, I forgot my umbrella. <groan> And just when I thought things couldn’t get worse, I spilled coffee all over my white shirt right before the presentation. <cough> But hey, at least I survived... kind of.",
12    "top_p": 0.95,
13    "voice": "dan",
14    "temperature": 0.6,
15    "max_new_tokens": 1200,
16    "repetition_penalty": 1.1
17}
18
19response = requests.post(url, headers=headers, json=data)
20
21if response.status_code == 200:
22    result = response.json()
23    print(json.dumps(result, indent=2))
24else:
25    print(f"Error: {response.status_code}")
26    print(response.text)

API Endpoint

POSThttps://api.segmind.com/v1/orpheus-3b-0.1

Parameters

textrequired

string

Input text to the model to convert to speech

max_new_tokensoptional

integer

Maximum number of tokens to generate

Default: 1200Range: 100 - 2000

repetition_penaltyoptional

number

Repetition penalty

Default: 1.1Range: 1 - 2

temperatureoptional

number

Temperature for generation. Controls expressiveness: 0.1–0.5 for stable speech, 0.6–1.0 for natural tone, 1.1–1.5 for expressive or dramatic voices.

Default: 0.6Range: 0.1 - 1.5

top_poptional

number

Top P for nucleus sampling. Recommended top-p: 0.2–0.4 for neutral tone, 0.6–0.8 for conversational, 0.8–1.0 for expressive, and 0.3–0.5 for assistants.

Default: 0.95Range: 0.1 - 1

voiceoptional

string

An enumeration.

Default: "dan"

Allowed values :

"tara""dan""josh""emma"

Response Type

Returns: Audio

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out