diff --git a/audio/audio.c b/audio/audio.c
index e18b5e98c5..9e9c03a42e 100644
--- a/audio/audio.c
+++ b/audio/audio.c
@@ -543,11 +543,43 @@ static size_t audio_pcm_hw_conv_in(HWVoiceIn *hw, void *pcm_buf, size_t samples)
 /*
  * Soft voice (capture)
  */
+static void audio_pcm_sw_resample_in(SWVoiceIn *sw,
+    size_t frames_in_max, size_t frames_out_max,
+    size_t *total_in, size_t *total_out)
+{
+    HWVoiceIn *hw = sw->hw;
+    struct st_sample *src, *dst;
+    size_t live, rpos, frames_in, frames_out;
+
+    live = hw->total_samples_captured - sw->total_hw_samples_acquired;
+    rpos = audio_ring_posb(hw->conv_buf.pos, live, hw->conv_buf.size);
+
+    /* resample conv_buf from rpos to end of buffer */
+    src = hw->conv_buf.buffer + rpos;
+    frames_in = MIN(frames_in_max, hw->conv_buf.size - rpos);
+    dst = sw->resample_buf.buffer;
+    frames_out = frames_out_max;
+    st_rate_flow(sw->rate, src, dst, &frames_in, &frames_out);
+    rpos += frames_in;
+    *total_in = frames_in;
+    *total_out = frames_out;
+
+    /* resample conv_buf from start of buffer if there are input frames left */
+    if (frames_in_max - frames_in && rpos == hw->conv_buf.size) {
+        src = hw->conv_buf.buffer;
+        frames_in = frames_in_max - frames_in;
+        dst += frames_out;
+        frames_out = frames_out_max - frames_out;
+        st_rate_flow(sw->rate, src, dst, &frames_in, &frames_out);
+        *total_in += frames_in;
+        *total_out += frames_out;
+    }
+}
+
 static size_t audio_pcm_sw_read(SWVoiceIn *sw, void *buf, size_t size)
 {
     HWVoiceIn *hw = sw->hw;
-    size_t samples, live, ret = 0, swlim, isamp, osamp, rpos, total = 0;
-    struct st_sample *src, *dst = sw->resample_buf.buffer;
+    size_t samples, live, ret, swlim, total;
 
     live = hw->total_samples_captured - sw->total_hw_samples_acquired;
     if (!live) {
@@ -558,33 +590,12 @@ static size_t audio_pcm_sw_read(SWVoiceIn *sw, void *buf, size_t size)
         return 0;
     }
 
-    rpos = audio_ring_posb(hw->conv_buf.pos, live, hw->conv_buf.size);
-
     samples = size / sw->info.bytes_per_frame;
 
     swlim = (live * sw->ratio) >> 32;
     swlim = MIN (swlim, samples);
 
-    while (swlim) {
-        src = hw->conv_buf.buffer + rpos;
-        if (hw->conv_buf.pos > rpos) {
-            isamp = hw->conv_buf.pos - rpos;
-        } else {
-            isamp = hw->conv_buf.size - rpos;
-        }
-
-        if (!isamp) {
-            break;
-        }
-        osamp = swlim;
-
-        st_rate_flow (sw->rate, src, dst, &isamp, &osamp);
-        swlim -= osamp;
-        rpos = (rpos + isamp) % hw->conv_buf.size;
-        dst += osamp;
-        ret += osamp;
-        total += isamp;
-    }
+    audio_pcm_sw_resample_in(sw, live, swlim, &total, &ret);
 
     if (!hw->pcm_ops->volume_in) {
         mixeng_volume(sw->resample_buf.buffer, ret, &sw->vol);