SLNG.AI API

Open Source @ SLNG

Endpoint:https://api.slng.ai

Orpheus

POST

https://api.slng.ai

/v1/tts/slng/orpheus

Generate audio from text using Orpheus voice model. English text-to-speech with 8 high-quality voices and emotion tag support. Real-time streaming supported. Audio format: 16-24kHz, 16-bit, mono WAV. Supports emotion tags like , , embedded in text.

Orpheus › Headers

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

Orpheus › Request Body

promptstring · required
The text to convert to speech

voicestring · enum
Voice to use. Available voices: 'tara' (female, conversational, clear), 'leah' (female, warm, gentle), 'jess' (female, energetic, youthful), 'leo' (male, authoritative, deep), 'dan' (male, friendly, casual), 'mia' (female, professional, articulate), 'zac' (male, enthusiastic, dynamic), 'zoe' (female, calm, soothing)
Enum values:
tara
leah
jess
leo
dan
mia
zac
zoe
Default: tara
max_tokensnumber
Maximum tokens to generate
Default: 2000
streamboolean
Whether to stream the response
Default: false

Orpheus › Responses

Audio response in WAV format

string · binary

Aura2 EN

POST

https://api.slng.ai

/v1/tts/slng/aura2-en

Deepgram Aura-2 English text-to-speech via SLNG Modal deployment. Streams natural voices with Deepgram's Aura-2 engine.

Aura2 EN › Headers

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

Aura2 EN › Request Body

textstring · required
Text to convert to speech

modelstring
Aura-2 model identifier (voice). Default aura-2-thalia-en
voicestring
Alias for model parameter
encodingstring
Audio encoding (linear16, mp3, opus)
Default: linear16
containerstring
Audio container (wav, mp3, none)
Default: none
sample_rateinteger
Sample rate in Hz
Default: 24000

Aura2 EN › Responses

Audio response

string · binary

Proprietary