org.llm4s.speech.stt.VoskSpeechToText
See theVoskSpeechToText companion object
Vosk-based speech-to-text implementation. Replaces Sphinx4 as it's more actively maintained and has better performance.
Value parameters
bufferSize
Buffer size for audio processing (bytes). Larger sizes may improve throughput.
modelPath
Path to the Vosk model directory. Defaults to standard Vosk model location.
targetSampleRate
Target sample rate for audio preprocessing (Hz). Vosk standard is 16000.
Attributes
Companion
object
Graph
Reset zoom Hide graph Show graph
Supertypes
class Object
trait Matchable
class Any
Members list
Close the cached Vosk model and release resources. Safe to call multiple times (idempotent). Should be called when the instance is no longer needed, especially in long-lived processes.
Close the cached Vosk model and release resources. Safe to call multiple times (idempotent). Should be called when the instance is no longer needed, especially in long-lived processes.
Attributes
Transcribe audio to text.
Transcribe audio to text.
Value parameters
input
Audio data to transcribe
options
Configuration for transcription
Attributes
Returns
Result containing Transcription or STTError
Throws
STTError
if transcription fails (wrapped in Result)
Definition Classes
Check if this provider is available/healthy. Useful for failover logic and availability checks.
Check if this provider is available/healthy. Useful for failover logic and availability checks.
Attributes
Inherited from:
SpeechToText
Unique identifier/name of this provider
Unique identifier/name of this provider
Attributes