Class TranscriptionCreateParams.ChunkingStrategy
-
- All Implemented Interfaces:
public final class TranscriptionCreateParams.ChunkingStrategy
Controls how the audio is cut into chunks. When set to
"auto"
, the server first normalizes loudness and then uses voice activity detection (VAD) to choose boundaries.server_vad
object can be provided to tweak VAD detection parameters manually. If unset, the audio is transcribed as a single block.
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description public interface
TranscriptionCreateParams.ChunkingStrategy.Visitor
An interface that defines how to map each variant of ChunkingStrategy to a value of type T.
public final class
TranscriptionCreateParams.ChunkingStrategy.VadConfig
-
Method Summary
Modifier and Type Method Description final Optional<JsonValue>
auto()
Automatically set chunking parameters based on the audio. final Optional<TranscriptionCreateParams.ChunkingStrategy.VadConfig>
vadConfig()
final Boolean
isAuto()
final Boolean
isVadConfig()
final JsonValue
asAuto()
Automatically set chunking parameters based on the audio. final TranscriptionCreateParams.ChunkingStrategy.VadConfig
asVadConfig()
final Optional<JsonValue>
_json()
final <T extends Any> T
accept(TranscriptionCreateParams.ChunkingStrategy.Visitor<T> visitor)
final TranscriptionCreateParams.ChunkingStrategy
validate()
final Boolean
isValid()
Boolean
equals(Object other)
Integer
hashCode()
String
toString()
final static TranscriptionCreateParams.ChunkingStrategy
ofAuto()
Automatically set chunking parameters based on the audio. final static TranscriptionCreateParams.ChunkingStrategy
ofVadConfig(TranscriptionCreateParams.ChunkingStrategy.VadConfig vadConfig)
-
-
Method Detail
-
auto
final Optional<JsonValue> auto()
Automatically set chunking parameters based on the audio. Must be set to
"auto"
.
-
vadConfig
final Optional<TranscriptionCreateParams.ChunkingStrategy.VadConfig> vadConfig()
-
isVadConfig
final Boolean isVadConfig()
-
asAuto
final JsonValue asAuto()
Automatically set chunking parameters based on the audio. Must be set to
"auto"
.
-
asVadConfig
final TranscriptionCreateParams.ChunkingStrategy.VadConfig asVadConfig()
-
accept
final <T extends Any> T accept(TranscriptionCreateParams.ChunkingStrategy.Visitor<T> visitor)
-
validate
final TranscriptionCreateParams.ChunkingStrategy validate()
-
ofAuto
final static TranscriptionCreateParams.ChunkingStrategy ofAuto()
Automatically set chunking parameters based on the audio. Must be set to
"auto"
.
-
ofVadConfig
final static TranscriptionCreateParams.ChunkingStrategy ofVadConfig(TranscriptionCreateParams.ChunkingStrategy.VadConfig vadConfig)
-
-
-
-