SLNG.
SLNG.AI API

Proprietary

Endpoint:https://api.slng.ai

Deepgram Aura

POST
https://api.slng.ai
/v1/tts/deepgram/aura

Deepgram Aura text-to-speech with natural voices

Deepgram Aura › 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.

Deepgram Aura › Request Body

  • textstring · required

    Text to convert to speech

  • voicestring

    Voice ID or name

  • languagestring

    Language code (e.g., en-US)

  • speednumber

    Speech speed (0.5 to 2.0)

Deepgram Aura › Responses

Audio response

string · binary

Cartesia Sonic

POST
https://api.slng.ai
/v1/tts/cartesia/sonic

Cartesia Sonic ultra-realistic text-to-speech with 90ms latency, voice cloning, and 15 language support

Cartesia Sonic › 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.

Cartesia Sonic › Request Body

  • textstring · required

    Text to convert to speech

  • voicestring

    Voice ID or name

  • languagestring

    Language code (e.g., en-US)

  • speednumber

    Speech speed (0.5 to 2.0)

Cartesia Sonic › Responses

Audio response

string · binary

ElevenLabs Multi-v2

POST
https://api.slng.ai
/v1/tts/elevenlabs/multi-v2

Generate audio from text using ElevenLabs Multi-v2 voice model. Multilingual model supporting 29+ languages with high-quality natural voices.

ElevenLabs Multi-v2 › 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.

ElevenLabs Multi-v2 › Request Body

  • textstring · required

    The text to convert to speech

  • voicestring

    Voice ID or name to use for synthesis

    Default: Rachel
  • voice_idstring

    Alternative parameter name for voice ID

  • languagestring

    Language code (en, es, fr, de, it, pt, pl, hi, ar, zh, ja, ko, etc.)

    Default: en
  • language_codestring

    Alternative parameter name for language code

  • streamboolean

    Whether to stream the audio response

    Default: false
  • formatstring

    Audio format to return (mp3_44100_128, mp3_44100_192, pcm_16000, pcm_22050, pcm_24000, pcm_44100, ulaw_8000)

    Default: mp3_44100_128
  • stabilitynumber · min: 0 · max: 1

    Voice stability (0.0-1.0)

    Default: 0.5
  • similarity_boostnumber · min: 0 · max: 1

    Voice similarity boost (0.0-1.0)

    Default: 0.75
  • stylenumber · min: 0 · max: 1

    Style control (0.0-1.0)

    Default: 0
  • speaking_ratenumber

    Speaking rate multiplier

    Default: 1
  • text_normalizationstring · enum

    Text normalization mode

    Enum values:
    auto
    on
    off
    Default: auto
  • seedinteger

    Random seed for reproducible audio generation

ElevenLabs Multi-v2 › Responses

Audio response

string · binary

ElevenLabs Turbo v2.5

POST
https://api.slng.ai
/v1/tts/elevenlabs/turbo-v2-5

Generate audio from text using ElevenLabs Turbo v2.5 voice model. Ultra-fast TTS model with low latency, ideal for real-time applications.

ElevenLabs Turbo v2.5 › 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.

ElevenLabs Turbo v2.5 › Request Body

  • textstring · required

    The text to convert to speech

  • voicestring

    Voice ID or name to use for synthesis

    Default: Rachel
  • voice_idstring

    Alternative parameter name for voice ID

  • languagestring

    Language code (en, es, fr, de, it, pt)

    Default: en
  • streamboolean

    Whether to stream the audio response

    Default: false
  • formatstring

    Audio format to return

    Default: mp3_44100_128
  • stabilitynumber · min: 0 · max: 1

    Voice stability (0.0-1.0)

    Default: 0.5
  • similarity_boostnumber · min: 0 · max: 1

    Voice similarity boost (0.0-1.0)

    Default: 0.75
  • speaking_ratenumber

    Speaking rate multiplier

    Default: 1
  • text_normalizationstring · enum

    Text normalization mode

    Enum values:
    auto
    on
    off
    Default: auto

ElevenLabs Turbo v2.5 › Responses

Audio response

string · binary

ElevenLabs TTV v3

POST
https://api.slng.ai
/v1/tts/elevenlabs/ttv-v3

Generate audio from text using ElevenLabs TTV v3 voice model. Optimized for synchronized text-to-video applications.

ElevenLabs TTV v3 › 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.

ElevenLabs TTV v3 › Request Body

  • textstring · required

    The text to convert to speech

  • voicestring

    Voice ID or name to use for synthesis

    Default: Rachel
  • voice_idstring

    Alternative parameter name for voice ID

  • languagestring

    Language code (en, es, fr, de, it, pt)

    Default: en
  • streamboolean

    Whether to stream the audio response

    Default: false
  • formatstring

    Audio format to return

    Default: mp3_44100_128
  • stabilitynumber · min: 0 · max: 1

    Voice stability (0.0-1.0)

    Default: 0.5
  • similarity_boostnumber · min: 0 · max: 1

    Voice similarity boost (0.0-1.0)

    Default: 0.75
  • speaking_ratenumber

    Speaking rate multiplier

    Default: 1
  • text_normalizationstring · enum

    Text normalization mode

    Enum values:
    auto
    on
    off
    Default: auto
  • seedinteger

    Random seed for reproducible audio generation

ElevenLabs TTV v3 › Responses

Audio response

string · binary

ElevenLabs Flash v2.5

POST
https://api.slng.ai
/v1/tts/elevenlabs/flash-v2-5

Generate audio from text using ElevenLabs Flash v2.5 voice model. Fast TTS model with good balance between speed and quality.

ElevenLabs Flash v2.5 › 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.

ElevenLabs Flash v2.5 › Request Body

  • textstring · required

    The text to convert to speech

  • voicestring

    Voice ID or name to use for synthesis

    Default: Rachel
  • voice_idstring

    Alternative parameter name for voice ID

  • languagestring

    Language code (en, es, fr, de, it, pt, pl)

    Default: en
  • streamboolean

    Whether to stream the audio response

    Default: false
  • formatstring

    Audio format to return

    Default: mp3_44100_128
  • stabilitynumber · min: 0 · max: 1

    Voice stability (0.0-1.0)

    Default: 0.5
  • similarity_boostnumber · min: 0 · max: 1

    Voice similarity boost (0.0-1.0)

    Default: 0.75
  • speaking_ratenumber

    Speaking rate multiplier

    Default: 1
  • text_normalizationstring · enum

    Text normalization mode

    Enum values:
    auto
    on
    off
    Default: auto

ElevenLabs Flash v2.5 › Responses

Audio response

string · binary
Open Source @ SLNG