Model RemoteStt

ml/remote/stt::RemoteStt


Parameters

↳ const api_key: Option<string>
↳ const backend: string = "openai"
↳ const base_url: string = ""
↳ const model: string = ""


Remote speech-to-text provider configuration.

Holds the connection parameters for a remote speech-to-text service.

  • backend: provider name (default "openai"); see the table below.
  • api_key: API key for authentication (omit for unauthenticated endpoints).
  • base_url: override the provider base URL (optional).
  • model: model identifier — see the table below for recommended values per backend.

Backends

backendapi_keyExample modelModel list
"openai"OpenAI API key"whisper-1"https://platform.openai.com/docs/models
"elevenlabs"ElevenLabs key"scribe_v1"https://elevenlabs.io/docs/speech-to-text

ℹ️ Use RemoteStt together with transcribe.

use ml/remote/stt::RemoteStt
use ml/remote/stt::transcribe

treatment example()
  model stt: RemoteStt(backend = "openai", api_key = "sk-...", model = "whisper-1")
  input  audio:      Stream<byte>
  output transcript: Block<string>
{
    transcribe[stt=stt]()
    Self.audio -> transcribe.audio,transcript -> Self.transcript
}