package vosk.stt.v1

Get desktop application:
View/edit binary Protocol Buffers messages

• rpc StreamingRecognize (stream StreamingRecognitionRequest, stream StreamingRecognitionResponse)

  stt_service.proto:8

  message StreamingRecognitionRequest

  stt_service.proto:12

  • oneof streaming_request

    • RecognitionConfig config = 1

    • bytes audio_content = 2

  message StreamingRecognitionResponse

  stt_service.proto:19

  • repeated SpeechRecognitionChunk chunks = 1

Used in: StreamingRecognitionRequest

• optional RecognitionSpec specification = 1

Used in: RecognitionConfig

• RecognitionSpec.AudioEncoding audio_encoding = 1

• int64 sample_rate_hertz = 2

  8000, 16000, 48000 only for pcm

• string language_code = 3

  code in BCP-47

• bool profanity_filter = 4

• string model = 5

• bool partial_results = 7

  If set true, tentative hypotheses may be returned as they become available (final=false flag) If false or omitted, only final=true result(s) are returned. Makes sense only for StreamingRecognize requests.

• bool single_utterance = 8

• bool raw_results = 10

  This mark allows disable normalization text

• int32 max_alternatives = 11

  Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of `SpeechRecognitionAlternative` messages within each `SpeechRecognitionResult`. The server may return fewer than `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of one. If omitted, will return a maximum of one.

• bool enable_word_time_offsets = 12

  If `true`, the top result includes a list of words and the start and end time offsets (timestamps) for those words. If `false`, no word-level time offset information is returned. The default is `false`.

Used in: RecognitionSpec

• AUDIO_ENCODING_UNSPECIFIED = 0

• LINEAR16_PCM = 1

  16-bit signed little-endian (Linear PCM)

Used in: SpeechRecognitionChunk

• string text = 1

• float confidence = 2

• repeated WordInfo words = 3

Used in: StreamingRecognitionResponse

• repeated SpeechRecognitionAlternative alternatives = 1

• bool final = 2

  This flag shows that the received chunk contains a part of the recognized text that won't be changed.

• bool end_of_utterance = 3

  This flag shows that the received chunk is the end of an utterance.

Used in: SpeechRecognitionAlternative

• optional google.protobuf.Duration start_time = 1

• optional google.protobuf.Duration end_time = 2

• string word = 3

• float confidence = 4