mirror of
https://github.com/jambonz/speech-utils.git
synced 2025-12-19 03:37:49 +00:00
37 lines
1.1 KiB
Protocol Buffer
37 lines
1.1 KiB
Protocol Buffer
// SPDX-FileCopyrightText: Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
syntax = "proto3";
|
|
|
|
package nvidia.riva;
|
|
|
|
option cc_enable_arenas = true;
|
|
option go_package = "nvidia.com/riva_speech";
|
|
|
|
/*
|
|
* AudioEncoding specifies the encoding of the audio bytes in the encapsulating message.
|
|
*/
|
|
enum AudioEncoding {
|
|
// Not specified.
|
|
ENCODING_UNSPECIFIED = 0;
|
|
|
|
// Uncompressed 16-bit signed little-endian samples (Linear PCM).
|
|
LINEAR_PCM = 1;
|
|
|
|
// `FLAC` (Free Lossless Audio
|
|
// Codec) is the recommended encoding because it is
|
|
// lossless--therefore recognition is not compromised--and
|
|
// requires only about half the bandwidth of `LINEAR16`. `FLAC` stream
|
|
// encoding supports 16-bit and 24-bit samples, however, not all fields in
|
|
// `STREAMINFO` are supported.
|
|
FLAC = 2;
|
|
|
|
// 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
|
|
MULAW = 3;
|
|
|
|
OGGOPUS = 4;
|
|
|
|
// 8-bit samples that compand 13-bit audio samples using G.711 PCMU/a-law.
|
|
ALAW = 20;
|
|
}
|