feat: Option to compress audio files by ~90%

Add option to reduce bandwidth (and potentially latency) by converting
voice recordings (wav) into a compressed audio format (webm or mp3).

Default behaviour is unchanged.

> File uploads are currently limited to 25 MB and the following input file
> types are supported: mp3, mp4, mpeg, mpga, m4a, wav, and webm.
>
> - https://platform.openai.com/docs/guides/speech-to-text

aider/voice.py

@@ -12,6 +12,7 @@ except (OSError, ModuleNotFoundError):
     sf = None
 
 from prompt_toolkit.shortcuts import prompt
+from pydub import AudioSegment
 
 from .dump import dump  # noqa: F401
 
@@ -27,7 +28,7 @@ class Voice:
 
     threshold = 0.15
 
-    def __init__(self):
+    def __init__(self, audio_format="wav"):
         if sf is None:
             raise SoundDeviceError
         try:
@@ -37,6 +38,9 @@ class Voice:
             self.sd = sd
         except (OSError, ModuleNotFoundError):
             raise SoundDeviceError
+        if audio_format not in ["wav", "mp3", "webm"]:
+            raise ValueError(f"Unsupported audio format: {audio_format}")
+        self.audio_format = audio_format
 
     def callback(self, indata, frames, time, status):
         """This is called (from a separate thread) for each audio block."""
@@ -80,7 +84,7 @@ class Voice:
     def raw_record_and_transcribe(self, history, language):
         self.q = queue.Queue()
 
-        filename = tempfile.mktemp(suffix=".wav")
+        temp_wav = tempfile.mktemp(suffix=".wav")
 
         try:
             sample_rate = int(self.sd.query_devices(None, "input")["default_samplerate"])
@@ -99,10 +103,18 @@ class Voice:
         except self.sd.PortAudioError as err:
             raise SoundDeviceError(f"Error accessing audio input device: {err}")
 
-        with sf.SoundFile(filename, mode="x", samplerate=sample_rate, channels=1) as file:
+        with sf.SoundFile(temp_wav, mode="x", samplerate=sample_rate, channels=1) as file:
             while not self.q.empty():
                 file.write(self.q.get())
 
+        if self.audio_format != "wav":
+            filename = tempfile.mktemp(suffix=f".{self.audio_format}")
+            audio = AudioSegment.from_wav(temp_wav)
+            audio.export(filename, format=self.audio_format)
+            os.remove(temp_wav)
+        else:
+            filename = temp_wav
+
         with open(filename, "rb") as fh:
             try:
                 transcript = litellm.transcription(
@@ -112,6 +124,9 @@ class Voice:
                 print(f"Unable to transcribe {filename}: {err}")
                 return
 
+        if self.audio_format != "wav":
+            os.remove(filename)
+
         text = transcript.text
         return text