Skip to main content
The SLNG Unified API accepts a common set of parameters across all providers. Some parameters are universal, others depend on the model. Provider-specific values (like voice identifiers or language codes) are passed through the same fields — the gateway forwards them to the underlying provider.

​
TTS parameters

ParameterTypeRequiredDescription
modelstringYesTarget model in provider/model:variant format
textstringYesText to synthesize
voicestringNoVoice identifier — accepted values depend on the provider and model
config.sample_rateintegerNoOutput sample rate in Hz
config.encodingstringNoOutput encoding format
config.languagestringNoLanguage code — accepted values depend on the provider
config.speednumberNoSpeech speed multiplier

​
TTS provider support

ParameterOrpheusRime ArcanaDeepgram Aura 2Sarvam Bulbul
voiceYesYesYesYes
config.sample_rateYesYesYesYes
config.encodingYesYesYesYes
config.language—YesYesYes
config.speed——Yes—

​
Provider-specific values

The voice and config.language fields accept provider-specific values. For example:
  • Orpheus voices: tara, leah, jess, leo, dan, mia
  • Deepgram Aura 2 voices: asteria-en, luna-en, athena-en
  • Rime Arcana language codes: en, fr, es, hi, ar, de
The gateway passes these values directly to the provider. If you send a voice identifier that the selected model does not support, the provider returns an error through the standard error response format.

​
Supported sample rates

All TTS models accept: 8000, 16000, 22050, 24000, 32000, 48000 Hz.

​
Supported encodings

All TTS models accept: linear16, mp3, opus, mulaw, alaw.

​
STT parameters

ParameterTypeRequiredDescription
audiofileYesAudio file to transcribe
languagestringNoLanguage code — accepted values depend on the provider
sample_rateintegerNoAudio sample rate in Hz
encodingstringNoAudio encoding format
enable_vadbooleanNoEnable voice activity detection
enable_partialsbooleanNoEnable partial transcription results

​
STT provider support

ParameterDeepgram Nova 3Whisper Large v3Deepgram Nova 2
languageYesAuto-detectYes
sample_rateYesYesYes
encodingYesYesYes
enable_vadYes—Yes
enable_partialsYes—Yes

​
Supported STT encodings

linear16, mp3, opus.

​
How provider-specific parameters work

The Unified API uses a schema-driven approach. All parameters are defined in the request schema — there is no generic passthrough or arbitrary key-value mechanism. The voice, language, and config fields accept provider-specific values as strings, and the gateway forwards them to the underlying provider without transformation. This means:
  • You use the same field names regardless of provider
  • Provider-specific values (voice names, language codes) go into the same fields
  • Validation happens at the provider level — if a value is not supported, you get a standard error response with the provider’s error message

​
Model identifiers

Models follow the pattern provider/model:variant for third-party and slng/provider/model:variant for SLNG-hosted. For example:
  • deepgram/aura:2 — third-party, proxied to Deepgram
  • slng/deepgram/aura:2 — SLNG-hosted Deepgram Aura 2
  • slng/canopylabs/orpheus:en — SLNG-hosted Orpheus English
For the full list of model identifiers, see Supported models.