FFmpeg
libspeexenc.c
Go to the documentation of this file.
1 /*
2  * Copyright (C) 2009 Justin Ruggles
3  * Copyright (c) 2009 Xuggle Incorporated
4  *
5  * This file is part of FFmpeg.
6  *
7  * FFmpeg is free software; you can redistribute it and/or
8  * modify it under the terms of the GNU Lesser General Public
9  * License as published by the Free Software Foundation; either
10  * version 2.1 of the License, or (at your option) any later version.
11  *
12  * FFmpeg is distributed in the hope that it will be useful,
13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15  * Lesser General Public License for more details.
16  *
17  * You should have received a copy of the GNU Lesser General Public
18  * License along with FFmpeg; if not, write to the Free Software
19  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20  */
21 
22 /**
23  * @file
24  * libspeex Speex audio encoder
25  *
26  * Usage Guide
27  * This explains the values that need to be set prior to initialization in
28  * order to control various encoding parameters.
29  *
30  * Channels
31  * Speex only supports mono or stereo, so avctx->ch_layout.nb_channels must
32  * be set to 1 or 2.
33  *
34  * Sample Rate / Encoding Mode
35  * Speex has 3 modes, each of which uses a specific sample rate.
36  * narrowband : 8 kHz
37  * wideband : 16 kHz
38  * ultra-wideband : 32 kHz
39  * avctx->sample_rate must be set to one of these 3 values. This will be
40  * used to set the encoding mode.
41  *
42  * Rate Control
43  * VBR mode is turned on by setting AV_CODEC_FLAG_QSCALE in avctx->flags.
44  * avctx->global_quality is used to set the encoding quality.
45  * For CBR mode, avctx->bit_rate can be used to set the constant bitrate.
46  * Alternatively, the 'cbr_quality' option can be set from 0 to 10 to set
47  * a constant bitrate based on quality.
48  * For ABR mode, set avctx->bit_rate and set the 'abr' option to 1.
49  * Approx. Bitrate Range:
50  * narrowband : 2400 - 25600 bps
51  * wideband : 4000 - 43200 bps
52  * ultra-wideband : 4400 - 45200 bps
53  *
54  * Complexity
55  * Encoding complexity is controlled by setting avctx->compression_level.
56  * The valid range is 0 to 10. A higher setting gives generally better
57  * quality at the expense of encoding speed. This does not affect the
58  * bit rate.
59  *
60  * Frames-per-Packet
61  * The encoder defaults to using 1 frame-per-packet. However, it is
62  * sometimes desirable to use multiple frames-per-packet to reduce the
63  * amount of container overhead. This can be done by setting the
64  * 'frames_per_packet' option to a value 1 to 8.
65  *
66  *
67  * Optional features
68  * Speex encoder supports several optional features, which can be useful
69  * for some conditions.
70  *
71  * Voice Activity Detection
72  * When enabled, voice activity detection detects whether the audio
73  * being encoded is speech or silence/background noise. VAD is always
74  * implicitly activated when encoding in VBR, so the option is only useful
75  * in non-VBR operation. In this case, Speex detects non-speech periods and
76  * encodes them with just enough bits to reproduce the background noise.
77  *
78  * Discontinuous Transmission (DTX)
79  * DTX is an addition to VAD/VBR operation, that makes it possible to stop transmitting
80  * completely when the background noise is stationary.
81  * In file-based operation only 5 bits are used for such frames.
82  */
83 
84 #include <speex/speex.h>
85 #include <speex/speex_header.h>
86 #include <speex/speex_stereo.h>
87 
89 #include "libavutil/common.h"
90 #include "libavutil/opt.h"
91 #include "avcodec.h"
92 #include "codec_internal.h"
93 #include "encode.h"
94 #include "audio_frame_queue.h"
95 
96 /* TODO: Think about converting abr, vad, dtx and such flags to a bit field */
97 typedef struct LibSpeexEncContext {
98  AVClass *class; ///< AVClass for private options
99  SpeexBits bits; ///< libspeex bitwriter context
100  SpeexHeader header; ///< libspeex header struct
101  void *enc_state; ///< libspeex encoder state
102  int frames_per_packet; ///< number of frames to encode in each packet
103  float vbr_quality; ///< VBR quality 0.0 to 10.0
104  int cbr_quality; ///< CBR quality 0 to 10
105  int abr; ///< flag to enable ABR
106  int vad; ///< flag to enable VAD
107  int dtx; ///< flag to enable DTX
108  int pkt_frame_count; ///< frame count for the current packet
109  AudioFrameQueue afq; ///< frame queue
111 
114 {
115  const char *mode_str = "unknown";
116 
117  av_log(avctx, AV_LOG_DEBUG, "channels: %d\n", avctx->ch_layout.nb_channels);
118  switch (s->header.mode) {
119  case SPEEX_MODEID_NB: mode_str = "narrowband"; break;
120  case SPEEX_MODEID_WB: mode_str = "wideband"; break;
121  case SPEEX_MODEID_UWB: mode_str = "ultra-wideband"; break;
122  }
123  av_log(avctx, AV_LOG_DEBUG, "mode: %s\n", mode_str);
124  if (s->header.vbr) {
125  av_log(avctx, AV_LOG_DEBUG, "rate control: VBR\n");
126  av_log(avctx, AV_LOG_DEBUG, " quality: %f\n", s->vbr_quality);
127  } else if (s->abr) {
128  av_log(avctx, AV_LOG_DEBUG, "rate control: ABR\n");
129  av_log(avctx, AV_LOG_DEBUG, " bitrate: %"PRId64" bps\n", avctx->bit_rate);
130  } else {
131  av_log(avctx, AV_LOG_DEBUG, "rate control: CBR\n");
132  av_log(avctx, AV_LOG_DEBUG, " bitrate: %"PRId64" bps\n", avctx->bit_rate);
133  }
134  av_log(avctx, AV_LOG_DEBUG, "complexity: %d\n",
135  avctx->compression_level);
136  av_log(avctx, AV_LOG_DEBUG, "frame size: %d samples\n",
137  avctx->frame_size);
138  av_log(avctx, AV_LOG_DEBUG, "frames per packet: %d\n",
139  s->frames_per_packet);
140  av_log(avctx, AV_LOG_DEBUG, "packet size: %d\n",
141  avctx->frame_size * s->frames_per_packet);
142  av_log(avctx, AV_LOG_DEBUG, "voice activity detection: %d\n", s->vad);
143  av_log(avctx, AV_LOG_DEBUG, "discontinuous transmission: %d\n", s->dtx);
144 }
145 
147 {
148  LibSpeexEncContext *s = avctx->priv_data;
149  int channels = avctx->ch_layout.nb_channels;
150  const SpeexMode *mode;
151  uint8_t *header_data;
152  int header_size;
153  int32_t complexity;
154 
155  /* channels */
157  av_log(avctx, AV_LOG_ERROR, "Invalid channels (%d). Only stereo and "
158  "mono are supported\n", channels);
159  return AVERROR(EINVAL);
160  }
161 
162  /* sample rate and encoding mode */
163  switch (avctx->sample_rate) {
164  case 8000: mode = speex_lib_get_mode(SPEEX_MODEID_NB); break;
165  case 16000: mode = speex_lib_get_mode(SPEEX_MODEID_WB); break;
166  case 32000: mode = speex_lib_get_mode(SPEEX_MODEID_UWB); break;
167  default:
168  av_log(avctx, AV_LOG_ERROR, "Sample rate of %d Hz is not supported. "
169  "Resample to 8, 16, or 32 kHz.\n", avctx->sample_rate);
170  return AVERROR(EINVAL);
171  }
172 
173  /* initialize libspeex */
174  s->enc_state = speex_encoder_init(mode);
175  if (!s->enc_state) {
176  av_log(avctx, AV_LOG_ERROR, "Error initializing libspeex\n");
177  return -1;
178  }
179  speex_init_header(&s->header, avctx->sample_rate, channels, mode);
180 
181  /* rate control method and parameters */
182  if (avctx->flags & AV_CODEC_FLAG_QSCALE) {
183  /* VBR */
184  s->header.vbr = 1;
185  s->vad = 1; /* VAD is always implicitly activated for VBR */
186  speex_encoder_ctl(s->enc_state, SPEEX_SET_VBR, &s->header.vbr);
187  s->vbr_quality = av_clipf(avctx->global_quality / (float)FF_QP2LAMBDA,
188  0.0f, 10.0f);
189  speex_encoder_ctl(s->enc_state, SPEEX_SET_VBR_QUALITY, &s->vbr_quality);
190  } else {
191  s->header.bitrate = avctx->bit_rate;
192  if (avctx->bit_rate > 0) {
193  /* CBR or ABR by bitrate */
194  if (s->abr) {
195  speex_encoder_ctl(s->enc_state, SPEEX_SET_ABR,
196  &s->header.bitrate);
197  speex_encoder_ctl(s->enc_state, SPEEX_GET_ABR,
198  &s->header.bitrate);
199  } else {
200  speex_encoder_ctl(s->enc_state, SPEEX_SET_BITRATE,
201  &s->header.bitrate);
202  speex_encoder_ctl(s->enc_state, SPEEX_GET_BITRATE,
203  &s->header.bitrate);
204  }
205  } else {
206  /* CBR by quality */
207  speex_encoder_ctl(s->enc_state, SPEEX_SET_QUALITY,
208  &s->cbr_quality);
209  speex_encoder_ctl(s->enc_state, SPEEX_GET_BITRATE,
210  &s->header.bitrate);
211  }
212  /* stereo side information adds about 800 bps to the base bitrate */
213  /* TODO: this should be calculated exactly */
214  avctx->bit_rate = s->header.bitrate + (channels == 2 ? 800 : 0);
215  }
216 
217  /* VAD is activated with VBR or can be turned on by itself */
218  if (s->vad)
219  speex_encoder_ctl(s->enc_state, SPEEX_SET_VAD, &s->vad);
220 
221  /* Activating Discontinuous Transmission */
222  if (s->dtx) {
223  speex_encoder_ctl(s->enc_state, SPEEX_SET_DTX, &s->dtx);
224  if (!(s->abr || s->vad || s->header.vbr))
225  av_log(avctx, AV_LOG_WARNING, "DTX is not much of use without ABR, VAD or VBR\n");
226  }
227 
228  /* set encoding complexity */
230  complexity = av_clip(avctx->compression_level, 0, 10);
231  speex_encoder_ctl(s->enc_state, SPEEX_SET_COMPLEXITY, &complexity);
232  }
233  speex_encoder_ctl(s->enc_state, SPEEX_GET_COMPLEXITY, &complexity);
234  avctx->compression_level = complexity;
235 
236  /* set packet size */
237  avctx->frame_size = s->header.frame_size;
238  s->header.frames_per_packet = s->frames_per_packet;
239 
240  /* set encoding delay */
241  speex_encoder_ctl(s->enc_state, SPEEX_GET_LOOKAHEAD, &avctx->initial_padding);
242  ff_af_queue_init(avctx, &s->afq);
243 
244  /* create header packet bytes from header struct */
245  /* note: libspeex allocates the memory for header_data, which is freed
246  below with speex_header_free() */
247  header_data = speex_header_to_packet(&s->header, &header_size);
248 
249  /* allocate extradata */
250  avctx->extradata = av_malloc(header_size + AV_INPUT_BUFFER_PADDING_SIZE);
251  if (!avctx->extradata) {
252  speex_header_free(header_data);
253  speex_encoder_destroy(s->enc_state);
254  av_log(avctx, AV_LOG_ERROR, "memory allocation error\n");
255  return AVERROR(ENOMEM);
256  }
257 
258  /* copy header packet to extradata */
259  memcpy(avctx->extradata, header_data, header_size);
260  avctx->extradata_size = header_size;
261  speex_header_free(header_data);
262 
263  /* init libspeex bitwriter */
264  speex_bits_init(&s->bits);
265 
266  print_enc_params(avctx, s);
267  return 0;
268 }
269 
270 static int encode_frame(AVCodecContext *avctx, AVPacket *avpkt,
271  const AVFrame *frame, int *got_packet_ptr)
272 {
273  LibSpeexEncContext *s = avctx->priv_data;
274  int16_t *samples = frame ? (int16_t *)frame->data[0] : NULL;
275  int ret;
276 
277  if (samples) {
278  /* encode Speex frame */
279  if (avctx->ch_layout.nb_channels == 2)
280  speex_encode_stereo_int(samples, s->header.frame_size, &s->bits);
281  speex_encode_int(s->enc_state, samples, &s->bits);
282  s->pkt_frame_count++;
283  if ((ret = ff_af_queue_add(&s->afq, frame)) < 0)
284  return ret;
285  } else {
286  /* handle end-of-stream */
287  if (!s->pkt_frame_count)
288  return 0;
289  /* add extra terminator codes for unused frames in last packet */
290  while (s->pkt_frame_count < s->frames_per_packet) {
291  speex_bits_pack(&s->bits, 15, 5);
292  s->pkt_frame_count++;
293  }
294  }
295 
296  /* write output if all frames for the packet have been encoded */
297  if (s->pkt_frame_count == s->frames_per_packet) {
298  s->pkt_frame_count = 0;
299  if ((ret = ff_alloc_packet(avctx, avpkt, speex_bits_nbytes(&s->bits))) < 0)
300  return ret;
301  ret = speex_bits_write(&s->bits, avpkt->data, avpkt->size);
302  speex_bits_reset(&s->bits);
303 
304  /* Get the next frame pts/duration */
305  ff_af_queue_remove(&s->afq, s->frames_per_packet * avctx->frame_size,
306  &avpkt->pts, &avpkt->duration);
307 
308  avpkt->size = ret;
309  *got_packet_ptr = 1;
310  return 0;
311  }
312  return 0;
313 }
314 
316 {
317  LibSpeexEncContext *s = avctx->priv_data;
318 
319  speex_bits_destroy(&s->bits);
320  speex_encoder_destroy(s->enc_state);
321 
322  ff_af_queue_close(&s->afq);
323 
324  return 0;
325 }
326 
327 #define OFFSET(x) offsetof(LibSpeexEncContext, x)
328 #define AE AV_OPT_FLAG_AUDIO_PARAM | AV_OPT_FLAG_ENCODING_PARAM
329 static const AVOption options[] = {
330  { "abr", "Use average bit rate", OFFSET(abr), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, AE },
331  { "cbr_quality", "Set quality value (0 to 10) for CBR", OFFSET(cbr_quality), AV_OPT_TYPE_INT, { .i64 = 8 }, 0, 10, AE },
332  { "frames_per_packet", "Number of frames to encode in each packet", OFFSET(frames_per_packet), AV_OPT_TYPE_INT, { .i64 = 1 }, 1, 8, AE },
333  { "vad", "Voice Activity Detection", OFFSET(vad), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, AE },
334  { "dtx", "Discontinuous Transmission", OFFSET(dtx), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, AE },
335  { NULL },
336 };
337 
338 static const AVClass speex_class = {
339  .class_name = "libspeex",
340  .item_name = av_default_item_name,
341  .option = options,
342  .version = LIBAVUTIL_VERSION_INT,
343 };
344 
345 static const FFCodecDefault defaults[] = {
346  { "b", "0" },
347  { "compression_level", "3" },
348  { NULL },
349 };
350 
352  .p.name = "libspeex",
353  .p.long_name = NULL_IF_CONFIG_SMALL("libspeex Speex"),
354  .p.type = AVMEDIA_TYPE_AUDIO,
355  .p.id = AV_CODEC_ID_SPEEX,
356  .caps_internal = FF_CODEC_CAP_NOT_INIT_THREADSAFE,
357  .priv_data_size = sizeof(LibSpeexEncContext),
358  .init = encode_init,
360  .close = encode_close,
361  .p.capabilities = AV_CODEC_CAP_DELAY,
362  .p.sample_fmts = (const enum AVSampleFormat[]){ AV_SAMPLE_FMT_S16,
364 #if FF_API_OLD_CHANNEL_LAYOUT
365  .p.channel_layouts = (const uint64_t[]){ AV_CH_LAYOUT_MONO,
367  0 },
368 #endif
369  .p.ch_layouts = (const AVChannelLayout[]) { AV_CHANNEL_LAYOUT_MONO,
371  { 0 },
372  },
373  .p.supported_samplerates = (const int[]){ 8000, 16000, 32000, 0 },
374  .p.priv_class = &speex_class,
375  .defaults = defaults,
376  .p.wrapper_name = "libspeex",
377 };
AVCodecContext::frame_size
int frame_size
Number of samples per channel in an audio frame.
Definition: avcodec.h:1035
ff_libspeex_encoder
const FFCodec ff_libspeex_encoder
Definition: libspeexenc.c:351
AV_LOG_WARNING
#define AV_LOG_WARNING
Something somehow does not look correct.
Definition: log.h:186
av_clip
#define av_clip
Definition: common.h:95
AVERROR
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later. That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another. Frame references ownership and permissions
opt.h
ff_af_queue_remove
void ff_af_queue_remove(AudioFrameQueue *afq, int nb_samples, int64_t *pts, int64_t *duration)
Remove frame(s) from the queue.
Definition: audio_frame_queue.c:75
AVCodecContext::sample_rate
int sample_rate
samples per second
Definition: avcodec.h:1007
ff_af_queue_close
void ff_af_queue_close(AudioFrameQueue *afq)
Close AudioFrameQueue.
Definition: audio_frame_queue.c:36
AV_CH_LAYOUT_MONO
#define AV_CH_LAYOUT_MONO
Definition: channel_layout.h:204
AV_CODEC_FLAG_QSCALE
#define AV_CODEC_FLAG_QSCALE
Use fixed qscale.
Definition: avcodec.h:216
ff_af_queue_init
av_cold void ff_af_queue_init(AVCodecContext *avctx, AudioFrameQueue *afq)
Initialize AudioFrameQueue.
Definition: audio_frame_queue.c:28
print_enc_params
static av_cold void print_enc_params(AVCodecContext *avctx, LibSpeexEncContext *s)
Definition: libspeexenc.c:112
AVFrame
This structure describes decoded (raw) audio or video data.
Definition: frame.h:325
AVPacket::data
uint8_t * data
Definition: packet.h:374
encode_close
static av_cold int encode_close(AVCodecContext *avctx)
Definition: libspeexenc.c:315
AVOption
AVOption.
Definition: opt.h:251
encode.h
AV_CHANNEL_LAYOUT_MONO
#define AV_CHANNEL_LAYOUT_MONO
Definition: channel_layout.h:353
FF_CODEC_CAP_NOT_INIT_THREADSAFE
#define FF_CODEC_CAP_NOT_INIT_THREADSAFE
The codec is not known to be init-threadsafe (i.e.
Definition: codec_internal.h:33
FFCodec
Definition: codec_internal.h:118
AVPacket::duration
int64_t duration
Duration of this packet in AVStream->time_base units, 0 if unknown.
Definition: packet.h:392
AV_CHANNEL_LAYOUT_STEREO
#define AV_CHANNEL_LAYOUT_STEREO
Definition: channel_layout.h:354
AVChannelLayout::nb_channels
int nb_channels
Number of channels in this layout.
Definition: channel_layout.h:300
FF_COMPRESSION_DEFAULT
#define FF_COMPRESSION_DEFAULT
Definition: avcodec.h:471
defaults
static const FFCodecDefault defaults[]
Definition: libspeexenc.c:345
av_malloc
#define av_malloc(s)
Definition: tableprint_vlc.h:30
init
static int init
Definition: av_tx.c:47
FFCodecDefault
Definition: codec_internal.h:88
FFCodec::p
AVCodec p
The public AVCodec.
Definition: codec_internal.h:122
AV_CODEC_ID_SPEEX
@ AV_CODEC_ID_SPEEX
Definition: codec_id.h:464
AVCodecContext::ch_layout
AVChannelLayout ch_layout
Audio channel layout.
Definition: avcodec.h:2065
audio_frame_queue.h
AVCodecContext::initial_padding
int initial_padding
Audio only.
Definition: avcodec.h:1732
AE
#define AE
Definition: libspeexenc.c:328
AVCodecContext::flags
int flags
AV_CODEC_FLAG_*.
Definition: avcodec.h:478
FF_CODEC_ENCODE_CB
#define FF_CODEC_ENCODE_CB(func)
Definition: codec_internal.h:269
ff_af_queue_add
int ff_af_queue_add(AudioFrameQueue *afq, const AVFrame *f)
Add a frame to the queue.
Definition: audio_frame_queue.c:44
AV_CH_LAYOUT_STEREO
#define AV_CH_LAYOUT_STEREO
Definition: channel_layout.h:205
AV_LOG_ERROR
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:180
av_cold
#define av_cold
Definition: attributes.h:90
LibSpeexEncContext::pkt_frame_count
int pkt_frame_count
frame count for the current packet
Definition: libspeexenc.c:108
AVCodecContext::extradata_size
int extradata_size
Definition: avcodec.h:500
s
#define s(width, name)
Definition: cbs_vp9.c:256
AVCodecContext::global_quality
int global_quality
Global quality for codecs which cannot change it per frame.
Definition: avcodec.h:464
LibSpeexEncContext::vad
int vad
flag to enable VAD
Definition: libspeexenc.c:106
AVMEDIA_TYPE_AUDIO
@ AVMEDIA_TYPE_AUDIO
Definition: avutil.h:202
AudioFrameQueue
Definition: audio_frame_queue.h:32
LibSpeexEncContext::abr
int abr
flag to enable ABR
Definition: libspeexenc.c:105
AV_LOG_DEBUG
#define AV_LOG_DEBUG
Stuff which is only useful for libav* developers.
Definition: log.h:201
channels
channels
Definition: aptx.h:32
options
static const AVOption options[]
Definition: libspeexenc.c:329
if
if(ret)
Definition: filter_design.txt:179
LIBAVUTIL_VERSION_INT
#define LIBAVUTIL_VERSION_INT
Definition: version.h:85
AVClass
Describe the class of an AVClass context structure.
Definition: log.h:66
NULL
#define NULL
Definition: coverity.c:32
LibSpeexEncContext::vbr_quality
float vbr_quality
VBR quality 0.0 to 10.0.
Definition: libspeexenc.c:103
AVCodecContext::bit_rate
int64_t bit_rate
the average bitrate
Definition: avcodec.h:448
av_default_item_name
const char * av_default_item_name(void *ptr)
Return the context name.
Definition: log.c:237
av_clipf
av_clipf
Definition: af_crystalizer.c:122
speex_class
static const AVClass speex_class
Definition: libspeexenc.c:338
AVPacket::size
int size
Definition: packet.h:375
NULL_IF_CONFIG_SMALL
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification.
Definition: internal.h:117
AVChannelLayout
An AVChannelLayout holds information about the channel layout of audio data.
Definition: channel_layout.h:290
codec_internal.h
LibSpeexEncContext::afq
AudioFrameQueue afq
frame queue
Definition: libspeexenc.c:109
AV_SAMPLE_FMT_NONE
@ AV_SAMPLE_FMT_NONE
Definition: samplefmt.h:56
LibSpeexEncContext::header
SpeexHeader header
libspeex header struct
Definition: libspeexenc.c:100
LibSpeexEncContext::bits
SpeexBits bits
libspeex bitwriter context
Definition: libspeexenc.c:99
LibSpeexEncContext::dtx
int dtx
flag to enable DTX
Definition: libspeexenc.c:107
AVPacket::pts
int64_t pts
Presentation timestamp in AVStream->time_base units; the time at which the decompressed packet will b...
Definition: packet.h:367
LibSpeexEncContext::frames_per_packet
int frames_per_packet
number of frames to encode in each packet
Definition: libspeexenc.c:102
AVCodecContext::extradata
uint8_t * extradata
some codecs need / can use extradata like Huffman tables.
Definition: avcodec.h:499
common.h
AVSampleFormat
AVSampleFormat
Audio sample formats.
Definition: samplefmt.h:55
AV_SAMPLE_FMT_S16
@ AV_SAMPLE_FMT_S16
signed 16 bits
Definition: samplefmt.h:58
AVCodec::name
const char * name
Name of the codec implementation.
Definition: codec.h:211
avcodec.h
ret
ret
Definition: filter_design.txt:187
AVClass::class_name
const char * class_name
The name of the class; usually it is the same name as the context structure type to which the AVClass...
Definition: log.h:71
frame
these buffered frames must be flushed immediately if a new input produces new the filter must not call request_frame to get more It must just process the frame or queue it The task of requesting more frames is left to the filter s request_frame method or the application If a filter has several the filter must be ready for frames arriving randomly on any input any filter with several inputs will most likely require some kind of queuing mechanism It is perfectly acceptable to have a limited queue and to drop frames when the inputs are too unbalanced request_frame For filters that do not use the this method is called when a frame is wanted on an output For a it should directly call filter_frame on the corresponding output For a if there are queued frames already one of these frames should be pushed If the filter should request a frame on one of its repeatedly until at least one frame has been pushed Return or at least make progress towards producing a frame
Definition: filter_design.txt:264
AV_INPUT_BUFFER_PADDING_SIZE
#define AV_INPUT_BUFFER_PADDING_SIZE
Definition: defs.h:40
encode_frame
static int encode_frame(AVCodecContext *avctx, AVPacket *avpkt, const AVFrame *frame, int *got_packet_ptr)
Definition: libspeexenc.c:270
AVCodecContext
main external API structure.
Definition: avcodec.h:398
channel_layout.h
OFFSET
#define OFFSET(x)
Definition: libspeexenc.c:327
mode
mode
Definition: ebur128.h:83
AV_OPT_TYPE_INT
@ AV_OPT_TYPE_INT
Definition: opt.h:225
AV_CODEC_CAP_DELAY
#define AV_CODEC_CAP_DELAY
Encoder or decoder requires flushing with NULL input at the end in order to give the complete and cor...
Definition: codec.h:82
samples
Filter the word “frame” indicates either a video frame or a group of audio samples
Definition: filter_design.txt:8
LibSpeexEncContext::enc_state
void * enc_state
libspeex encoder state
Definition: libspeexenc.c:101
AVPacket
This structure stores compressed data.
Definition: packet.h:351
AVCodecContext::priv_data
void * priv_data
Definition: avcodec.h:425
LibSpeexEncContext::cbr_quality
int cbr_quality
CBR quality 0 to 10.
Definition: libspeexenc.c:104
int32_t
int32_t
Definition: audioconvert.c:56
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:27
LibSpeexEncContext
Definition: libspeexenc.c:97
encode_init
static av_cold int encode_init(AVCodecContext *avctx)
Definition: libspeexenc.c:146
FF_QP2LAMBDA
#define FF_QP2LAMBDA
factor to convert from H.263 QP to lambda
Definition: avutil.h:227
ff_alloc_packet
int ff_alloc_packet(AVCodecContext *avctx, AVPacket *avpkt, int64_t size)
Check AVPacket size and allocate data.
Definition: encode.c:35
AVCodecContext::compression_level
int compression_level
Definition: avcodec.h:470
SpeexMode
Definition: speexdec.c:167