aboutsummaryrefslogtreecommitdiff
path: root/webrtc/modules/audio_device/include/audio_device_defines.h
blob: 3ebbd23cc5f664d3fda73c697cbae7d53d4bc77a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
/*
 *  Copyright (c) 2011 The WebRTC project authors. All Rights Reserved.
 *
 *  Use of this source code is governed by a BSD-style license
 *  that can be found in the LICENSE file in the root of the source
 *  tree. An additional intellectual property rights grant can be found
 *  in the file PATENTS.  All contributing project authors may
 *  be found in the AUTHORS file in the root of the source tree.
 */

#ifndef WEBRTC_MODULES_AUDIO_DEVICE_INCLUDE_AUDIO_DEVICE_DEFINES_H_
#define WEBRTC_MODULES_AUDIO_DEVICE_INCLUDE_AUDIO_DEVICE_DEFINES_H_

#include <stddef.h>

#include "webrtc/typedefs.h"

namespace webrtc {

static const int kAdmMaxDeviceNameSize = 128;
static const int kAdmMaxFileNameSize = 512;
static const int kAdmMaxGuidSize = 128;

static const int kAdmMinPlayoutBufferSizeMs = 10;
static const int kAdmMaxPlayoutBufferSizeMs = 250;

// ----------------------------------------------------------------------------
//  AudioDeviceObserver
// ----------------------------------------------------------------------------

class AudioDeviceObserver {
 public:
  enum ErrorCode { kRecordingError = 0, kPlayoutError = 1 };
  enum WarningCode { kRecordingWarning = 0, kPlayoutWarning = 1 };

  virtual void OnErrorIsReported(const ErrorCode error) = 0;
  virtual void OnWarningIsReported(const WarningCode warning) = 0;

 protected:
  virtual ~AudioDeviceObserver() {}
};

// ----------------------------------------------------------------------------
//  AudioTransport
// ----------------------------------------------------------------------------

class AudioTransport {
 public:
  virtual int32_t RecordedDataIsAvailable(const void* audioSamples,
                                          const size_t nSamples,
                                          const size_t nBytesPerSample,
                                          const uint8_t nChannels,
                                          const uint32_t samplesPerSec,
                                          const uint32_t totalDelayMS,
                                          const int32_t clockDrift,
                                          const uint32_t currentMicLevel,
                                          const bool keyPressed,
                                          uint32_t& newMicLevel) = 0;

  virtual int32_t NeedMorePlayData(const size_t nSamples,
                                   const size_t nBytesPerSample,
                                   const uint8_t nChannels,
                                   const uint32_t samplesPerSec,
                                   void* audioSamples,
                                   size_t& nSamplesOut,
                                   int64_t* elapsed_time_ms,
                                   int64_t* ntp_time_ms) = 0;

  // Method to pass captured data directly and unmixed to network channels.
  // |channel_ids| contains a list of VoE channels which are the
  // sinks to the capture data. |audio_delay_milliseconds| is the sum of
  // recording delay and playout delay of the hardware. |current_volume| is
  // in the range of [0, 255], representing the current microphone analog
  // volume. |key_pressed| is used by the typing detection.
  // |need_audio_processing| specify if the data needs to be processed by APM.
  // Currently WebRtc supports only one APM, and Chrome will make sure only
  // one stream goes through APM. When |need_audio_processing| is false, the
  // values of |audio_delay_milliseconds|, |current_volume| and |key_pressed|
  // will be ignored.
  // The return value is the new microphone volume, in the range of |0, 255].
  // When the volume does not need to be updated, it returns 0.
  // TODO(xians): Remove this interface after Chrome and Libjingle switches
  // to OnData().
  virtual int OnDataAvailable(const int voe_channels[],
                              int number_of_voe_channels,
                              const int16_t* audio_data,
                              int sample_rate,
                              int number_of_channels,
                              size_t number_of_frames,
                              int audio_delay_milliseconds,
                              int current_volume,
                              bool key_pressed,
                              bool need_audio_processing) {
    return 0;
  }

  // Method to pass the captured audio data to the specific VoE channel.
  // |voe_channel| is the id of the VoE channel which is the sink to the
  // capture data.
  // TODO(xians): Remove this interface after Libjingle switches to
  // PushCaptureData().
  virtual void OnData(int voe_channel,
                      const void* audio_data,
                      int bits_per_sample,
                      int sample_rate,
                      int number_of_channels,
                      size_t number_of_frames) {}

  // Method to push the captured audio data to the specific VoE channel.
  // The data will not undergo audio processing.
  // |voe_channel| is the id of the VoE channel which is the sink to the
  // capture data.
  // TODO(xians): Make the interface pure virtual after Libjingle
  // has its implementation.
  virtual void PushCaptureData(int voe_channel,
                               const void* audio_data,
                               int bits_per_sample,
                               int sample_rate,
                               int number_of_channels,
                               size_t number_of_frames) {}

  // Method to pull mixed render audio data from all active VoE channels.
  // The data will not be passed as reference for audio processing internally.
  // TODO(xians): Support getting the unmixed render data from specific VoE
  // channel.
  virtual void PullRenderData(int bits_per_sample,
                              int sample_rate,
                              int number_of_channels,
                              size_t number_of_frames,
                              void* audio_data,
                              int64_t* elapsed_time_ms,
                              int64_t* ntp_time_ms) {}

 protected:
  virtual ~AudioTransport() {}
};

// Helper class for storage of fundamental audio parameters such as sample rate,
// number of channels, native buffer size etc.
// Note that one audio frame can contain more than one channel sample and each
// sample is assumed to be a 16-bit PCM sample. Hence, one audio frame in
// stereo contains 2 * (16/8) = 4 bytes of data.
class AudioParameters {
 public:
  // This implementation does only support 16-bit PCM samples.
  static const size_t kBitsPerSample = 16;
  AudioParameters()
      : sample_rate_(0),
        channels_(0),
        frames_per_buffer_(0),
        frames_per_10ms_buffer_(0) {}
  AudioParameters(int sample_rate, int channels, size_t frames_per_buffer)
      : sample_rate_(sample_rate),
        channels_(channels),
        frames_per_buffer_(frames_per_buffer),
        frames_per_10ms_buffer_(static_cast<size_t>(sample_rate / 100)) {}
  void reset(int sample_rate, int channels, size_t frames_per_buffer) {
    sample_rate_ = sample_rate;
    channels_ = channels;
    frames_per_buffer_ = frames_per_buffer;
    frames_per_10ms_buffer_ = static_cast<size_t>(sample_rate / 100);
  }
  size_t bits_per_sample() const { return kBitsPerSample; }
  void reset(int sample_rate, int channels, double ms_per_buffer) {
    reset(sample_rate, channels,
          static_cast<size_t>(sample_rate * ms_per_buffer + 0.5));
  }
  void reset(int sample_rate, int channels) {
    reset(sample_rate, channels, static_cast<size_t>(0));
  }
  int sample_rate() const { return sample_rate_; }
  int channels() const { return channels_; }
  size_t frames_per_buffer() const { return frames_per_buffer_; }
  size_t frames_per_10ms_buffer() const { return frames_per_10ms_buffer_; }
  size_t GetBytesPerFrame() const { return channels_ * kBitsPerSample / 8; }
  size_t GetBytesPerBuffer() const {
    return frames_per_buffer_ * GetBytesPerFrame();
  }
  // The WebRTC audio device buffer (ADB) only requires that the sample rate
  // and number of channels are configured. Hence, to be "valid", only these
  // two attributes must be set.
  bool is_valid() const { return ((sample_rate_ > 0) && (channels_ > 0)); }
  // Most platforms also require that a native buffer size is defined.
  // An audio parameter instance is considered to be "complete" if it is both
  // "valid" (can be used by the ADB) and also has a native frame size.
  bool is_complete() const { return (is_valid() && (frames_per_buffer_ > 0)); }
  size_t GetBytesPer10msBuffer() const {
    return frames_per_10ms_buffer_ * GetBytesPerFrame();
  }
  double GetBufferSizeInMilliseconds() const {
    if (sample_rate_ == 0)
      return 0.0;
    return frames_per_buffer_ / (sample_rate_ / 1000.0);
  }
  double GetBufferSizeInSeconds() const {
    if (sample_rate_ == 0)
      return 0.0;
    return static_cast<double>(frames_per_buffer_) / (sample_rate_);
  }

 private:
  int sample_rate_;
  int channels_;
  size_t frames_per_buffer_;
  size_t frames_per_10ms_buffer_;
};

}  // namespace webrtc

#endif  // WEBRTC_MODULES_AUDIO_DEVICE_INCLUDE_AUDIO_DEVICE_DEFINES_H_