void CreateSound()
{
// Sound source needs a node so that it is considered enabled
node = new Node();
SoundSource source = node.CreateComponent <SoundSource>();
soundStream = new BufferedSoundStream();
// Set format: 44100 Hz, sixteen bit, mono
soundStream.SetFormat(44100, true, false);
// Start playback. We don't have data in the stream yet, but the SoundSource will wait until there is data,
// as the stream is by default in the "don't stop at end" mode
source.Play(soundStream);
}
// https://github.com/microsoft/MixedRealityCompanionKit/blob/master/LegacySpectatorView/Samples/SharedHolograms/Assets/HoloToolkit/Utilities/Scripts/TextToSpeech.cs
private async Task <BufferedSoundStream> SpeechStreamToSoundStream(SpeechSynthesisStream inStream)
{
var outStream = new BufferedSoundStream();
uint size = (uint)inStream.Size;
byte[] wavAudio = new byte[size];
using (var inputStream = inStream.GetInputStreamAt(0)) {
inStream.Dispose();
using (var reader = new DataReader(inputStream)) {
await reader.LoadAsync(size);
reader.ReadBytes(wavAudio);
}
}
int channelCount = wavAudio[22];
int frequency = BytesToInt(wavAudio, 24);
outStream.SetFormat((uint)frequency, true, channelCount == 2);
// Get past all the other sub chunks to get to the data subchunk:
int pos = 12; // First subchunk ID from 12 to 16
// Keep iterating until we find the data chunk (i.e. 64 61 74 61 ...... (i.e. 100 97 116 97 in decimal))
while (!(wavAudio[pos] == 100 && wavAudio[pos + 1] == 97 && wavAudio[pos + 2] == 116 && wavAudio[pos + 3] == 97))
{
pos += 4;
int chunkSize = wavAudio[pos] + wavAudio[pos + 1] * 256 + wavAudio[pos + 2] * 65536 + wavAudio[pos + 3] * 16777216;
pos += 4 + chunkSize;
}
pos += 8;
// Pos is now positioned to start of actual sound data.
int sampleCount = (wavAudio.Length - pos) / 2; // 2 bytes per sample (16 bit sound mono)
if (channelCount == 2)
{
sampleCount /= 2;
} // 4 bytes per sample (16 bit stereo)
outStream.AddData(wavAudio, pos);
return(outStream);
}
