diff --git a/src/audio/aria/aria.c b/src/audio/aria/aria.c
index 0c9ffee5dd39..dc265cfac240 100644
--- a/src/audio/aria/aria.c
+++ b/src/audio/aria/aria.c
@@ -168,11 +168,6 @@ static void aria_set_stream_params(struct comp_buffer *buffer,
 	const struct ipc4_audio_format *audio_fmt = &mod->priv.cfg.base_cfg.audio_fmt;
 
 	ipc4_update_buffer_format(buffer, audio_fmt);
-#if SOF_USE_HIFI(3, ARIA) || SOF_USE_HIFI(4, ARIA)
-	audio_stream_set_align(8, 1, &buffer->stream);
-#elif SOF_USE_HIFI(5, ARIA)
-	audio_stream_set_align(16, 1, &buffer->stream);
-#endif
 }
 
 static int aria_prepare(struct processing_module *mod,
@@ -195,6 +190,7 @@ static int aria_prepare(struct processing_module *mod,
 
 	aria_set_stream_params(source, mod);
 	aria_set_stream_params(sink, mod);
+	audio_stream_set_align(SOF_FRAME_BYTE_ALIGN, SOF_FRAME_COUNT_ALIGN, &source->stream);
 
 	if (audio_stream_get_valid_fmt(&source->stream) != SOF_IPC_FRAME_S24_4LE ||
 	    audio_stream_get_valid_fmt(&sink->stream) != SOF_IPC_FRAME_S24_4LE) {
diff --git a/src/audio/audio_stream.c b/src/audio/audio_stream.c
index c4c5f7b04acb..aa16617f066c 100644
--- a/src/audio/audio_stream.c
+++ b/src/audio/audio_stream.c
@@ -51,6 +51,6 @@ void audio_stream_init(struct audio_stream *audio_stream, void *buff_addr, uint3
 	audio_stream->addr = buff_addr;
 	audio_stream->end_addr = (char *)audio_stream->addr + size;
 
-	audio_stream_set_align(1, 1, audio_stream);
+	audio_stream_set_align(SOF_FRAME_BYTE_ALIGN, SOF_FRAME_COUNT_ALIGN, audio_stream);
 	audio_stream_reset(audio_stream);
 }
diff --git a/src/audio/eq_fir/eq_fir.c b/src/audio/eq_fir/eq_fir.c
index 39cce7fd7974..5427e99ff1ac 100644
--- a/src/audio/eq_fir/eq_fir.c
+++ b/src/audio/eq_fir/eq_fir.c
@@ -369,11 +369,10 @@ static int eq_fir_process(struct processing_module *mod,
 static void eq_fir_set_alignment(struct audio_stream *source,
 				 struct audio_stream *sink)
 {
-	const uint32_t byte_align = 1;
+	const uint32_t byte_align = SOF_FRAME_BYTE_ALIGN;
 	const uint32_t frame_align_req = 2; /* Process multiples of 2 frames */
 
 	audio_stream_set_align(byte_align, frame_align_req, source);
-	audio_stream_set_align(byte_align, frame_align_req, sink);
 }
 
 static int eq_fir_prepare(struct processing_module *mod,
diff --git a/src/audio/eq_iir/eq_iir.c b/src/audio/eq_iir/eq_iir.c
index 0f07fbeda03c..016c2c8caf82 100644
--- a/src/audio/eq_iir/eq_iir.c
+++ b/src/audio/eq_iir/eq_iir.c
@@ -142,7 +142,7 @@ static int eq_iir_process(struct processing_module *mod,
 static void eq_iir_set_alignment(struct audio_stream *source,
 				 struct audio_stream *sink)
 {
-	const uint32_t byte_align = 8;
+	const uint32_t byte_align = SOF_FRAME_BYTE_ALIGN;
 	const uint32_t frame_align_req = 2;
 
 	audio_stream_set_align(byte_align, frame_align_req, source);
diff --git a/src/audio/igo_nr/igo_nr.c b/src/audio/igo_nr/igo_nr.c
index bde7d2b8fe32..e398af7d964b 100644
--- a/src/audio/igo_nr/igo_nr.c
+++ b/src/audio/igo_nr/igo_nr.c
@@ -832,8 +832,7 @@ static int32_t igo_nr_prepare(struct processing_module *mod,
 	if (ret)
 		return ret;
 
-	source_set_alignment_constants(source, 1, IGO_FRAME_SIZE);
-	sink_set_alignment_constants(sink, 1, IGO_FRAME_SIZE);
+	source_set_alignment_constants(source, SOF_FRAME_BYTE_ALIGN, IGO_FRAME_SIZE);
 
 	igo_nr_set_igo_params(mod);
 
diff --git a/src/audio/mixer/mixer.c b/src/audio/mixer/mixer.c
index 6300d5b86bc5..cdc74fd2f1e7 100644
--- a/src/audio/mixer/mixer.c
+++ b/src/audio/mixer/mixer.c
@@ -187,18 +187,18 @@ static int mixer_reset(struct processing_module *mod)
 /* init and calculate the aligned setting for available frames and free frames retrieve*/
 static inline void mixer_set_frame_alignment(struct audio_stream *source)
 {
-#if XCHAL_HAVE_HIFI3 || XCHAL_HAVE_HIFI4
 
 	/* Xtensa intrinsics ask for 8-byte aligned. 5.1 format SSE audio
-	 * requires 16-byte aligned.
+	 * requires 16-byte aligned. Note: The SOF_FRAME_BYTE_ALIGN is the
+	 * same value 16 with HiFi5.
 	 */
-	const uint32_t byte_align = audio_stream_get_channels(source) == 6 ? 16 : 8;
+	const uint32_t byte_align = audio_stream_get_channels(source) == 6 ?
+		MIXER_HIFI_FRAME_BYTE_ALIGN_6CH : SOF_FRAME_BYTE_ALIGN;
 
 	/*There is no limit for frame number, so set it as 1*/
-	const uint32_t frame_align_req = 1;
+	const uint32_t frame_align_req = SOF_FRAME_COUNT_ALIGN;
 
 	audio_stream_set_align(byte_align, frame_align_req, source);
-#endif
 }
 
 static int mixer_prepare(struct processing_module *mod,
@@ -216,7 +216,6 @@ static int mixer_prepare(struct processing_module *mod,
 	}
 
 	md->mix_func = mixer_get_processing_function(dev, sink);
-	mixer_set_frame_alignment(&sink->stream);
 
 	/* check each mixer source state */
 	struct comp_buffer *source;
diff --git a/src/audio/mixer/mixer.h b/src/audio/mixer/mixer.h
index 118aaf1c914f..875ddcbb26fe 100644
--- a/src/audio/mixer/mixer.h
+++ b/src/audio/mixer/mixer.h
@@ -32,6 +32,9 @@ void sys_comp_module_mixer_interface_init(void);
 
 #define MIXER_MAX_SOURCES	2
 
+/* Xtensa HiFi optimized version needs this for 5.1ch */
+#define MIXER_HIFI_FRAME_BYTE_ALIGN_6CH 16
+
 /* mixer component private data */
 struct mixer_data {
 	void (*mix_func)(struct comp_dev *dev, struct audio_stream *sink,
diff --git a/src/audio/selector/selector.c b/src/audio/selector/selector.c
index 8d99d785a899..6afc92d8bdfc 100644
--- a/src/audio/selector/selector.c
+++ b/src/audio/selector/selector.c
@@ -1007,8 +1007,7 @@ static int selector_prepare(struct processing_module *mod,
 	sourceb = comp_dev_get_first_data_producer(dev);
 	sinkb = comp_dev_get_first_data_consumer(dev);
 
-	audio_stream_set_align(4, 1, &sourceb->stream);
-	audio_stream_set_align(4, 1, &sinkb->stream);
+	audio_stream_set_align(SOF_FRAME_BYTE_ALIGN, SOF_FRAME_COUNT_ALIGN, &sourceb->stream);
 
 	/* get source data format and period bytes */
 	cd->source_format = audio_stream_get_frm_fmt(&sourceb->stream);
diff --git a/src/audio/src/src_common.c b/src/audio/src/src_common.c
index cb595f3e8877..3a9c7dac280f 100644
--- a/src/audio/src/src_common.c
+++ b/src/audio/src/src_common.c
@@ -384,13 +384,12 @@ int src_copy_sxx(struct comp_data *cd, struct sof_source *source,
 	return -ENOTSUP;
 }
 
-void src_set_alignment(struct sof_source *source, struct sof_sink *sink)
+void src_set_alignment(struct sof_source *source)
 {
-	const uint32_t byte_align = 1;
-	const uint32_t frame_align_req = 1;
+	const uint32_t byte_align = SOF_FRAME_BYTE_ALIGN;
+	const uint32_t frame_align_req = SOF_FRAME_COUNT_ALIGN;
 
 	source_set_alignment_constants(source, byte_align, frame_align_req);
-	sink_set_alignment_constants(sink, byte_align, frame_align_req);
 }
 
 static int src_verify_params(struct processing_module *mod)
diff --git a/src/audio/src/src_common.h b/src/audio/src/src_common.h
index ae3c60574eec..98f29a263131 100644
--- a/src/audio/src/src_common.h
+++ b/src/audio/src/src_common.h
@@ -143,7 +143,7 @@ int32_t src_input_rates(void);
 
 int32_t src_output_rates(void);
 
-void src_set_alignment(struct sof_source *source, struct sof_sink *sink);
+void src_set_alignment(struct sof_source *source);
 
 struct comp_data {
 #if CONFIG_IPC_MAJOR_4
diff --git a/src/audio/src/src_ipc3.c b/src/audio/src/src_ipc3.c
index b161155193fc..541efcdb24be 100644
--- a/src/audio/src/src_ipc3.c
+++ b/src/audio/src/src_ipc3.c
@@ -105,7 +105,7 @@ int src_prepare_general(struct processing_module *mod,
 	enum sof_ipc_frame sink_format;
 
 	/* set align requirements */
-	src_set_alignment(source, sink);
+	src_set_alignment(source);
 
 	/* get source/sink data format */
 	source_format = source_get_frm_fmt(source);
diff --git a/src/audio/src/src_ipc4.c b/src/audio/src/src_ipc4.c
index 1240a86bd48e..91f286347a5f 100644
--- a/src/audio/src/src_ipc4.c
+++ b/src/audio/src/src_ipc4.c
@@ -151,7 +151,7 @@ int src_prepare_general(struct processing_module *mod,
 	int ret = 0;
 
 	/* set align requirements */
-	src_set_alignment(source, sink);
+	src_set_alignment(source);
 
 	switch (cd->ipc_config.base.audio_fmt.valid_bit_depth) {
 #if CONFIG_FORMAT_S16LE
diff --git a/src/audio/tdfb/tdfb.c b/src/audio/tdfb/tdfb.c
index fa6a207d49e6..69998c390ed2 100644
--- a/src/audio/tdfb/tdfb.c
+++ b/src/audio/tdfb/tdfb.c
@@ -692,11 +692,10 @@ static int tdfb_process(struct processing_module *mod,
 static void tdfb_set_alignment(struct audio_stream *source,
 			       struct audio_stream *sink)
 {
-	const uint32_t byte_align = 1;
+	const uint32_t byte_align = SOF_FRAME_BYTE_ALIGN;
 	const uint32_t frame_align_req = 2; /* Process multiples of 2 frames */
 
 	audio_stream_set_align(byte_align, frame_align_req, source);
-	audio_stream_set_align(byte_align, frame_align_req, sink);
 }
 
 static int tdfb_prepare(struct processing_module *mod,
diff --git a/src/audio/volume/volume.c b/src/audio/volume/volume.c
index aed356a3ec83..d44dbde6752f 100644
--- a/src/audio/volume/volume.c
+++ b/src/audio/volume/volume.c
@@ -556,6 +556,7 @@ static int volume_process(struct processing_module *mod,
 			  struct output_stream_buffer *output_buffers, int num_output_buffers)
 {
 	struct vol_data *cd = module_get_private_data(mod);
+	struct audio_stream *source = input_buffers[0].data;
 	uint32_t avail_frames = input_buffers[0].size;
 	uint32_t frames;
 	int64_t prev_sum = 0;
@@ -571,12 +572,23 @@ static int volume_process(struct processing_module *mod,
 			frames = avail_frames;
 		} else if (cd->ramp_type == SOF_VOLUME_LINEAR_ZC) {
 			/* with ZC ramping look for next ZC offset */
-			frames = cd->zc_get(input_buffers[0].data, cd->vol_ramp_frames, &prev_sum);
+			frames = cd->zc_get(source, cd->vol_ramp_frames, &prev_sum);
+			/* Align frames count to audio stream constraints */
+			frames = audio_stream_align_frames_round_up(source, frames);
 		} else {
-			/* without ZC process max ramp chunk */
-			frames = cd->vol_ramp_frames;
+			/* During volume ramp align the number of frames used in this
+			 * gain step. Align up since with low rates this would typically
+			 * become zero.
+			 */
+			frames = audio_stream_align_frames_round_up(source, cd->vol_ramp_frames);
 		}
 
+		/* Cancel the gain step for ZC or smaller ramp step if it exceeds
+		 * the available frames.
+		 */
+		if (frames > avail_frames)
+			frames = avail_frames;
+
 		if (!cd->ramp_finished) {
 			volume_ramp(mod);
 			cd->vol_ramp_elapsed_frames += frames;
@@ -625,28 +637,34 @@ static vol_zc_func vol_get_zc_function(struct comp_dev *dev,
  * \param[in,out] source Structure pointer of source.
  * \param[in,out] sink Structure pointer of sink.
  */
-static void volume_set_alignment(struct audio_stream *source,
-				 struct audio_stream *sink)
+static void volume_set_alignment(struct audio_stream *source)
 {
+	const int channels = audio_stream_get_channels(source);
+
 	/* Both source and sink buffer in HiFi5  processing version,
 	 * xtensa intrinsics ask for 16-byte aligned.
+	 * Note: The SOF_FRAME_BYTE_ALIGN is the same value 16 with HiFi5
 	 *
 	 * Both source and sink buffer in HiFi3 or HiFi4 processing version,
 	 * xtensa intrinsics ask for 8-byte aligned. 5.1 format SSE audio
 	 * requires 16-byte aligned.
 	 */
-#if SOF_USE_HIFI(3, VOLUME) || SOF_USE_HIFI(4, VOLUME)
-	const uint32_t byte_align = audio_stream_get_channels(source) == 6 ?
-		VOLUME_HIFI3_HIFI4_FRAME_BYTE_ALIGN_6CH : SOF_FRAME_BYTE_ALIGN;
+	const uint32_t byte_align =
+		(channels == 6) ? VOLUME_HIFI3_HIFI4_FRAME_BYTE_ALIGN_6CH : SOF_FRAME_BYTE_ALIGN;
+
+	/* On HiFi5 the number of samples to process must be multiple of four for s32
+	 * and multiple of eight for s16. For HiFi4 and HiFi3 the number of samples
+	 * need to be multiple of two for s32 and multiple of four for s16.
+	 */
+#if SOF_USE_HIFI(5, VOLUME)
+	const int n = (audio_stream_get_valid_fmt(source) == SOF_IPC_FRAME_S16_LE) ? 8 : 4;
 #else
-	const uint32_t byte_align = SOF_FRAME_BYTE_ALIGN;
+	const int n = (audio_stream_get_valid_fmt(source) == SOF_IPC_FRAME_S16_LE) ? 4 : 2;
 #endif
 
-	/*There is no limit for frame number, so both source and sink set it to be 1*/
-	const uint32_t frame_align_req = 1;
+	const uint32_t frame_align_req = (uint32_t)(n / gcd(n, channels));
 
 	audio_stream_set_align(byte_align, frame_align_req, source);
-	audio_stream_set_align(byte_align, frame_align_req, sink);
 }
 
 /**
@@ -682,7 +700,7 @@ static int volume_prepare(struct processing_module *mod,
 
 	ret = volume_peak_prepare(cd, mod);
 
-	volume_set_alignment(&sourceb->stream, &sinkb->stream);
+	volume_set_alignment(&sourceb->stream);
 
 	/* get sink period bytes */
 	sink_period_bytes = audio_stream_period_bytes(&sinkb->stream,
diff --git a/src/include/sof/audio/audio_stream.h b/src/include/sof/audio/audio_stream.h
index 9703ec9cadea..4fe97cda55a9 100644
--- a/src/include/sof/audio/audio_stream.h
+++ b/src/include/sof/audio/audio_stream.h
@@ -591,9 +591,9 @@ audio_stream_avail_frames(const struct audio_stream *source,
 }
 
 /**
- * Computes maximum number of frames aligned that can be copied from
- * source buffer to sink buffer, verifying number of available source
- * frames vs. free space available in sink.
+ * Computes maximum number of frames aligned with source align criteria
+ * that can be copied from source buffer to sink buffer, verifying number
+ * of available source frames vs. free space available in sink.
  * @param source Buffer of source.
  * @param sink Buffer of sink.
  * @return Number of frames.
@@ -602,14 +602,45 @@ static inline uint32_t
 audio_stream_avail_frames_aligned(const struct audio_stream *source,
 				  const struct audio_stream *sink)
 {
-	uint32_t src_frames = (audio_stream_get_avail_bytes(source) >>
-			source->runtime_stream_params.align_shift_idx) *
-					source->runtime_stream_params.align_frame_cnt;
-	uint32_t sink_frames = (audio_stream_get_free_bytes(sink) >>
-			sink->runtime_stream_params.align_shift_idx) *
-					sink->runtime_stream_params.align_frame_cnt;
+	int src_frames = audio_stream_get_avail_frames(source);
+	int sink_frames = audio_stream_get_free_frames(sink);
+	int n = MIN(src_frames, sink_frames);
 
-	return MIN(src_frames, sink_frames);
+	return (uint32_t)((n * audio_stream_frame_bytes(source) >>
+			   source->runtime_stream_params.align_shift_idx) *
+			  source->runtime_stream_params.align_frame_cnt);
+}
+
+/**
+ * Rounds down a frame count to meet the alignment constraint of the stream.
+ * @param stream Audio stream with alignment requirements set.
+ * @param frames Frame count to round down.
+ * @return Largest aligned frame count less than or equal to frames.
+ */
+static inline uint32_t audio_stream_align_frames_round_down(const struct audio_stream *stream,
+							    uint32_t frames)
+{
+	uint16_t align = stream->runtime_stream_params.align_frame_cnt;
+
+	return (frames / align) * align;
+}
+
+/**
+ * Rounds up a frame count to meet the alignment constraint of the stream.
+ * @param stream Audio stream with alignment requirements set.
+ * @param frames Frame count to round up.
+ * @return Smallest aligned frame count greater than or equal to frames.
+ */
+static inline uint32_t audio_stream_align_frames_round_up(const struct audio_stream *stream,
+							  uint32_t frames)
+{
+	uint16_t align = stream->runtime_stream_params.align_frame_cnt;
+	uint32_t aligned_frames = (frames / align) * align;
+
+	if (aligned_frames < frames)
+		aligned_frames += align;
+
+	return aligned_frames;
 }
 
 /**
diff --git a/src/include/sof/common.h b/src/include/sof/common.h
index 4bb279b039aa..28c49644fd62 100644
--- a/src/include/sof/common.h
+++ b/src/include/sof/common.h
@@ -223,6 +223,9 @@
 #  define SOF_FRAME_BYTE_ALIGN	4
 #endif
 
+/* Default frames count align is one */
+#define SOF_FRAME_COUNT_ALIGN	1
+
 #ifndef __GLIBC_USE
 #define __GLIBC_USE(x) 0
 #endif