Skip to main content
WSS
/
v1
/
stt
/
soniox
/
speech-ai:rt-v4

Documentation Index

Fetch the complete documentation index at: https://docs.slng.ai/llms.txt

Use this file to discover all available pages before exploring further.

Messages
bearer
type:http

API key issued by SLNG. Pass as Authorization: Bearer <token> in the WebSocket upgrade request headers.

method
type:string

GET

headers
type:object
X-World-Part-Override
type:enum

Target world part override. Auto-selected if not provided. Available world parts: ap, eu, na.

Available options: ap, eu, na
Init Request (Soniox)
type:object

Initialize a Soniox STT session with provider-specific recognition configuration.

Binary Audio Frame
type:string

Stream raw binary audio frames to be transcribed. Sent as binary WebSocket frames (NOT JSON) — no envelope, no base64 encoding. Frame format must match the audio_format, sample_rate, and num_channels declared in the init message (default pcm_s16le at 16kHz mono).

Finalize Message
type:object

Force-finalize buffered audio tokens without closing the connection.

Keepalive Message
type:object

Keep the WebSocket connection alive during silence.

Close Message
type:object

Signal end of audio stream.

Tokens Frame (Soniox native)
type:object

Native Soniox tokens frame forwarded unchanged from the upstream provider.

Error Frame (Soniox native)
type:object

Native Soniox error frame forwarded unchanged from the upstream provider.