echogarden 0.12.2 → 1.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +15 -14
- package/data/schemas/options.json +398 -111
- package/dist/alignment/DTWMfccSequenceAlignment.d.ts +1 -1
- package/dist/alignment/DTWMfccSequenceAlignment.js +8 -8
- package/dist/alignment/DTWSequenceAlignment.d.ts +1 -1
- package/dist/alignment/DTWSequenceAlignment.js +1 -1
- package/dist/alignment/DTWSequenceAlignmentWindowed.d.ts +1 -1
- package/dist/alignment/DTWSequenceAlignmentWindowed.js +2 -2
- package/dist/alignment/LevenshteinSequenceAlignment.d.ts +1 -1
- package/dist/alignment/LevenshteinSequenceAlignment.js +1 -1
- package/dist/alignment/SpeechAlignment.d.ts +9 -10
- package/dist/alignment/SpeechAlignment.js +136 -105
- package/dist/alignment/SpeechAlignment.js.map +1 -1
- package/dist/api/API.d.ts +13 -12
- package/dist/api/API.js +14 -13
- package/dist/api/API.js.map +1 -1
- package/dist/api/APIOptions.d.ts +5 -4
- package/dist/api/Alignment.d.ts +15 -9
- package/dist/api/Alignment.js +88 -74
- package/dist/api/Alignment.js.map +1 -1
- package/dist/api/Common.js +1 -1
- package/dist/api/Denoising.d.ts +6 -6
- package/dist/api/Denoising.js +23 -23
- package/dist/api/Denoising.js.map +1 -1
- package/dist/api/LanguageDetection.d.ts +19 -12
- package/dist/api/LanguageDetection.js +88 -38
- package/dist/api/LanguageDetection.js.map +1 -1
- package/dist/api/Recognition.d.ts +16 -6
- package/dist/api/Recognition.js +129 -55
- package/dist/api/Recognition.js.map +1 -1
- package/dist/api/SourceSeparation.d.ts +17 -0
- package/dist/api/SourceSeparation.js +61 -0
- package/dist/api/SourceSeparation.js.map +1 -0
- package/dist/api/Synthesis.d.ts +18 -18
- package/dist/api/Synthesis.js +191 -164
- package/dist/api/Synthesis.js.map +1 -1
- package/dist/api/Translation.d.ts +19 -8
- package/dist/api/Translation.js +132 -35
- package/dist/api/Translation.js.map +1 -1
- package/dist/api/Vad.d.ts +10 -5
- package/dist/api/Vad.js +76 -38
- package/dist/api/Vad.js.map +1 -1
- package/dist/audio/AudioBufferConversion.d.ts +1 -1
- package/dist/audio/AudioBufferConversion.js +4 -4
- package/dist/audio/AudioPlayer.d.ts +1 -1
- package/dist/audio/AudioPlayer.js +26 -26
- package/dist/audio/AudioPlayer.js.map +1 -1
- package/dist/audio/AudioRecorder.d.ts +1 -1
- package/dist/audio/AudioRecorder.js +5 -5
- package/dist/audio/AudioUtilities.d.ts +13 -9
- package/dist/audio/AudioUtilities.js +86 -24
- package/dist/audio/AudioUtilities.js.map +1 -1
- package/dist/cli/CLI.d.ts +3 -3
- package/dist/cli/CLI.js +271 -162
- package/dist/cli/CLI.js.map +1 -1
- package/dist/cli/CLIConfigFile.js +8 -8
- package/dist/cli/CLILauncher.js +6 -6
- package/dist/cli/CLIOptionsSchema.js +2 -2
- package/dist/cli/CLIParser.js +5 -5
- package/dist/cli/CLIStarter.js +4 -4
- package/dist/codecs/FFMpegTranscoder.d.ts +2 -2
- package/dist/codecs/FFMpegTranscoder.js +37 -37
- package/dist/codecs/FFMpegTranscoder.js.map +1 -1
- package/dist/codecs/TIMITCodec.js +5 -5
- package/dist/codecs/WaveCodec.d.ts +1 -1
- package/dist/codecs/WaveCodec.js +22 -22
- package/dist/denoising/RNNoise.d.ts +1 -1
- package/dist/denoising/RNNoise.js +9 -9
- package/dist/dsp/BiquadFilter.d.ts +3 -2
- package/dist/dsp/BiquadFilter.js +18 -11
- package/dist/dsp/BiquadFilter.js.map +1 -1
- package/dist/dsp/DecayingPeakEstimator.d.ts +16 -0
- package/dist/dsp/DecayingPeakEstimator.js +23 -0
- package/dist/dsp/DecayingPeakEstimator.js.map +1 -0
- package/dist/dsp/FFT.d.ts +8 -4
- package/dist/dsp/FFT.js +76 -30
- package/dist/dsp/FFT.js.map +1 -1
- package/dist/dsp/KWeightingFilter.d.ts +9 -0
- package/dist/dsp/KWeightingFilter.js +40 -0
- package/dist/dsp/KWeightingFilter.js.map +1 -0
- package/dist/dsp/LoudnessEstimator.d.ts +21 -0
- package/dist/dsp/LoudnessEstimator.js +47 -0
- package/dist/dsp/LoudnessEstimator.js.map +1 -0
- package/dist/dsp/MFCC.d.ts +2 -2
- package/dist/dsp/MFCC.js +15 -15
- package/dist/dsp/MelSpectogram.d.ts +1 -1
- package/dist/dsp/MelSpectogram.js +6 -6
- package/dist/dsp/Rubberband.d.ts +11 -11
- package/dist/dsp/Rubberband.js +27 -27
- package/dist/dsp/Sonic.d.ts +1 -1
- package/dist/dsp/Sonic.js +3 -3
- package/dist/dsp/SpeexResampler.d.ts +1 -1
- package/dist/dsp/SpeexResampler.js +2 -2
- package/dist/math/VectorMath.d.ts +12 -8
- package/dist/math/VectorMath.js +35 -32
- package/dist/math/VectorMath.js.map +1 -1
- package/dist/nlp/ChineseSegmentation.js +2 -2
- package/dist/nlp/CompromiseNLP.js +3 -3
- package/dist/nlp/EspeakPhonemizer.js +30 -30
- package/dist/nlp/IPA.js +20 -20
- package/dist/nlp/JapaneseSegmentation.js +6 -6
- package/dist/nlp/Lexicon.d.ts +1 -1
- package/dist/nlp/Lexicon.js +7 -7
- package/dist/nlp/Segmentation.d.ts +3 -0
- package/dist/nlp/Segmentation.js +21 -14
- package/dist/nlp/Segmentation.js.map +1 -1
- package/dist/nlp/TextNormalizer.js +16 -16
- package/dist/recognition/AmazonTranscribeSTT.d.ts +2 -2
- package/dist/recognition/AmazonTranscribeSTT.js +13 -14
- package/dist/recognition/AmazonTranscribeSTT.js.map +1 -1
- package/dist/recognition/AzureCognitiveServicesSTT.js +5 -6
- package/dist/recognition/AzureCognitiveServicesSTT.js.map +1 -1
- package/dist/recognition/GoogleCloudSTT.d.ts +3 -3
- package/dist/recognition/GoogleCloudSTT.js +18 -18
- package/dist/recognition/OpenAICloudSTT.d.ts +19 -0
- package/dist/recognition/OpenAICloudSTT.js +81 -0
- package/dist/recognition/OpenAICloudSTT.js.map +1 -0
- package/dist/recognition/SileroSTT.d.ts +2 -2
- package/dist/recognition/SileroSTT.js +25 -25
- package/dist/recognition/VoskSTT.d.ts +2 -2
- package/dist/recognition/VoskSTT.js +8 -8
- package/dist/recognition/WhisperCppSTT.d.ts +88 -0
- package/dist/recognition/WhisperCppSTT.js +332 -0
- package/dist/recognition/WhisperCppSTT.js.map +1 -0
- package/dist/recognition/WhisperSTT.d.ts +49 -25
- package/dist/recognition/WhisperSTT.js +626 -481
- package/dist/recognition/WhisperSTT.js.map +1 -1
- package/dist/server/Client.d.ts +1 -1
- package/dist/server/Client.js +22 -22
- package/dist/server/Server.js +9 -9
- package/dist/server/Server.js.map +1 -1
- package/dist/server/Worker.d.ts +22 -22
- package/dist/server/Worker.js +36 -36
- package/dist/server/Worker.js.map +1 -1
- package/dist/server/WorkerStarter.js +2 -2
- package/dist/source-separation/MDXNetSourceSeparation.d.ts +11 -0
- package/dist/source-separation/MDXNetSourceSeparation.js +161 -0
- package/dist/source-separation/MDXNetSourceSeparation.js.map +1 -0
- package/dist/speech-language-detection/SileroLanguageDetection.d.ts +1 -1
- package/dist/speech-language-detection/SileroLanguageDetection.js +7 -7
- package/dist/subtitles/Subtitles.d.ts +10 -0
- package/dist/subtitles/Subtitles.js +2 -2
- package/dist/subtitles/Subtitles.js.map +1 -1
- package/dist/synthesis/AwsPollyTTS.d.ts +1 -1
- package/dist/synthesis/AwsPollyTTS.js +12 -12
- package/dist/synthesis/AzureCognitiveServicesTTS.js +7 -7
- package/dist/synthesis/CoquiServerTTS.js +10 -10
- package/dist/synthesis/CoquiServerTTS.js.map +1 -1
- package/dist/synthesis/ElevenlabsTTS.d.ts +23 -0
- package/dist/synthesis/ElevenlabsTTS.js +103 -0
- package/dist/synthesis/ElevenlabsTTS.js.map +1 -0
- package/dist/synthesis/EspeakTTS.d.ts +6 -5
- package/dist/synthesis/EspeakTTS.js +81 -69
- package/dist/synthesis/EspeakTTS.js.map +1 -1
- package/dist/synthesis/FliteTTS.d.ts +3 -3
- package/dist/synthesis/FliteTTS.js +154 -154
- package/dist/synthesis/FliteTTS.js.map +1 -1
- package/dist/synthesis/GoogleCloudTTS.d.ts +3 -3
- package/dist/synthesis/GoogleCloudTTS.js +17 -17
- package/dist/synthesis/GoogleCloudTTS.js.map +1 -1
- package/dist/synthesis/GoogleTranslateTTS.d.ts +1 -1
- package/dist/synthesis/GoogleTranslateTTS.js +103 -103
- package/dist/synthesis/MicrosoftEdgeTTS.d.ts +2 -2
- package/dist/synthesis/MicrosoftEdgeTTS.js +74 -74
- package/dist/synthesis/OpenAICloudTTS.d.ts +13 -0
- package/dist/synthesis/OpenAICloudTTS.js +169 -0
- package/dist/synthesis/OpenAICloudTTS.js.map +1 -0
- package/dist/synthesis/SamTTS.js +3 -3
- package/dist/synthesis/SapiTTS.d.ts +3 -3
- package/dist/synthesis/SapiTTS.js +26 -26
- package/dist/synthesis/StreamlabsPollyTTS.d.ts +2 -2
- package/dist/synthesis/StreamlabsPollyTTS.js +27 -27
- package/dist/synthesis/SvoxPicoTTS.d.ts +2 -2
- package/dist/synthesis/SvoxPicoTTS.js +65 -65
- package/dist/synthesis/SvoxPicoTTS.js.map +1 -1
- package/dist/synthesis/VitsTTS.d.ts +3 -3
- package/dist/synthesis/VitsTTS.js +378 -378
- package/dist/synthesis/VitsTTS.js.map +1 -1
- package/dist/tests/Test.js +2 -2
- package/dist/utilities/Compression.d.ts +5 -0
- package/dist/utilities/Compression.js +29 -13
- package/dist/utilities/Compression.js.map +1 -1
- package/dist/utilities/FileDownloader.d.ts +1 -1
- package/dist/utilities/FileDownloader.js +16 -16
- package/dist/utilities/FileSystem.js +7 -7
- package/dist/utilities/Locale.d.ts +7 -7
- package/dist/utilities/Locale.js +15 -15
- package/dist/utilities/Logger.js +3 -3
- package/dist/utilities/ObjectUtilities.js +19 -19
- package/dist/utilities/OpenPromise.js +2 -2
- package/dist/utilities/OpenPromise.js.map +1 -1
- package/dist/utilities/PackageManager.js +31 -0
- package/dist/utilities/PackageManager.js.map +1 -1
- package/dist/utilities/PathUtilities.js +8 -8
- package/dist/utilities/RandomGenerator.js +2 -2
- package/dist/utilities/SmoothEstimator.d.ts +8 -0
- package/dist/utilities/SmoothEstimator.js +25 -0
- package/dist/utilities/SmoothEstimator.js.map +1 -0
- package/dist/utilities/TarballMaker.js +8 -8
- package/dist/utilities/Timeline.d.ts +3 -2
- package/dist/utilities/Timeline.js +11 -11
- package/dist/utilities/Timeline.js.map +1 -1
- package/dist/utilities/Timer.js +4 -4
- package/dist/utilities/Utilities.d.ts +4 -0
- package/dist/utilities/Utilities.js +38 -15
- package/dist/utilities/Utilities.js.map +1 -1
- package/dist/utilities/WasmMemoryManager.js +7 -7
- package/dist/utilities/WebReader.js +23 -23
- package/dist/utilities/WikipediaReader.js +2 -2
- package/dist/voice-activity-detection/AdaptiveGateVAD.d.ts +28 -0
- package/dist/voice-activity-detection/AdaptiveGateVAD.js +138 -0
- package/dist/voice-activity-detection/AdaptiveGateVAD.js.map +1 -0
- package/dist/voice-activity-detection/SileroVAD.d.ts +1 -1
- package/dist/voice-activity-detection/SileroVAD.js +5 -5
- package/dist/voice-activity-detection/SileroVAD.js.map +1 -1
- package/dist/voice-activity-detection/WebRtcVAD.d.ts +1 -1
- package/dist/voice-activity-detection/WebRtcVAD.js +4 -4
- package/docs/API.md +29 -11
- package/docs/CLI.md +31 -7
- package/docs/Contributing.md +38 -0
- package/docs/Development.md +93 -19
- package/docs/Engines.md +28 -16
- package/docs/Licenses.md +4 -1
- package/docs/Options.md +158 -78
- package/docs/Releases.md +262 -0
- package/docs/Server.md +7 -7
- package/docs/Tasklist.md +95 -76
- package/docs/Technical.md +4 -4
- package/package.json +13 -14
- package/src/alignment/DTWMfccSequenceAlignment.ts +9 -9
- package/src/alignment/DTWSequenceAlignment.ts +2 -2
- package/src/alignment/DTWSequenceAlignmentWindowed.ts +3 -3
- package/src/alignment/LevenshteinSequenceAlignment.ts +2 -2
- package/src/alignment/SpeechAlignment.ts +204 -119
- package/src/api/API.ts +14 -13
- package/src/api/APIOptions.ts +12 -11
- package/src/api/Alignment.ts +147 -90
- package/src/api/Common.ts +1 -1
- package/src/api/Denoising.ts +28 -28
- package/src/api/LanguageDetection.ts +135 -48
- package/src/api/Recognition.ts +198 -59
- package/src/api/SourceSeparation.ts +99 -0
- package/src/api/Synthesis.ts +217 -181
- package/src/api/Translation.ts +193 -40
- package/src/api/Vad.ts +110 -41
- package/src/audio/AudioBufferConversion.ts +4 -4
- package/src/audio/AudioPlayer.ts +27 -27
- package/src/audio/AudioRecorder.ts +5 -5
- package/src/audio/AudioUtilities.ts +107 -24
- package/src/cli/CLI.ts +313 -164
- package/src/cli/CLIConfigFile.ts +8 -8
- package/src/cli/CLILauncher.ts +6 -6
- package/src/cli/CLIOptionsSchema.ts +2 -2
- package/src/cli/CLIParser.ts +5 -5
- package/src/cli/CLIStarter.ts +4 -4
- package/src/codecs/FFMpegTranscoder.ts +38 -38
- package/src/codecs/TIMITCodec.ts +5 -5
- package/src/codecs/WaveCodec.ts +22 -22
- package/src/denoising/RNNoise.ts +9 -9
- package/src/dsp/BiquadFilter.ts +19 -11
- package/src/dsp/DecayingPeakEstimator.ts +35 -0
- package/src/dsp/FFT.ts +103 -35
- package/src/dsp/KWeightingFilter.ts +43 -0
- package/src/dsp/LoudnessEstimator.ts +74 -0
- package/src/dsp/MFCC.ts +15 -15
- package/src/dsp/MelSpectogram.ts +7 -7
- package/src/dsp/Rubberband.ts +38 -38
- package/src/dsp/Sonic.ts +4 -4
- package/src/dsp/SpeexResampler.ts +2 -2
- package/src/math/VectorMath.ts +42 -33
- package/src/nlp/ChineseSegmentation.ts +3 -3
- package/src/nlp/CompromiseNLP.ts +3 -3
- package/src/nlp/EspeakPhonemizer.ts +30 -30
- package/src/nlp/IPA.ts +20 -20
- package/src/nlp/JapaneseSegmentation.ts +6 -6
- package/src/nlp/Lexicon.ts +8 -8
- package/src/nlp/Segmentation.ts +23 -14
- package/src/nlp/TextNormalizer.ts +16 -16
- package/src/recognition/AmazonTranscribeSTT.ts +16 -17
- package/src/recognition/AzureCognitiveServicesSTT.ts +8 -6
- package/src/recognition/GoogleCloudSTT.ts +21 -21
- package/src/recognition/OpenAICloudSTT.ts +142 -0
- package/src/recognition/SileroSTT.ts +26 -26
- package/src/recognition/VoskSTT.ts +10 -10
- package/src/recognition/WhisperCppSTT.ts +555 -0
- package/src/recognition/WhisperSTT.ts +760 -507
- package/src/server/Client.ts +23 -23
- package/src/server/Server.ts +9 -9
- package/src/server/Worker.ts +53 -53
- package/src/server/WorkerStarter.ts +2 -2
- package/src/source-separation/MDXNetSourceSeparation.ts +228 -0
- package/src/speech-language-detection/SileroLanguageDetection.ts +8 -8
- package/src/subtitles/Subtitles.ts +3 -3
- package/src/synthesis/AwsPollyTTS.ts +14 -14
- package/src/synthesis/AzureCognitiveServicesTTS.ts +10 -10
- package/src/synthesis/CoquiServerTTS.ts +10 -10
- package/src/synthesis/ElevenlabsTTS.ts +137 -0
- package/src/synthesis/EspeakTTS.ts +90 -71
- package/src/synthesis/FliteTTS.ts +157 -157
- package/src/synthesis/GoogleCloudTTS.ts +19 -19
- package/src/synthesis/GoogleTranslateTTS.ts +104 -104
- package/src/synthesis/MicrosoftEdgeTTS.ts +80 -80
- package/src/synthesis/OpenAICloudTTS.ts +196 -0
- package/src/synthesis/SamTTS.ts +3 -3
- package/src/synthesis/SapiTTS.ts +29 -29
- package/src/synthesis/StreamlabsPollyTTS.ts +29 -29
- package/src/synthesis/SvoxPicoTTS.ts +67 -67
- package/src/synthesis/VitsTTS.ts +380 -380
- package/src/tests/Test.ts +4 -4
- package/src/utilities/Compression.ts +34 -13
- package/src/utilities/FileDownloader.ts +19 -19
- package/src/utilities/FileSystem.ts +7 -7
- package/src/utilities/Locale.ts +22 -22
- package/src/utilities/Logger.ts +4 -4
- package/src/utilities/ObjectUtilities.ts +19 -19
- package/src/utilities/OpenPromise.ts +2 -2
- package/src/utilities/PackageManager.ts +40 -0
- package/src/utilities/PathUtilities.ts +8 -8
- package/src/utilities/RandomGenerator.ts +3 -3
- package/src/utilities/SmoothEstimator.ts +35 -0
- package/src/utilities/TarballMaker.ts +9 -9
- package/src/utilities/Timeline.ts +15 -13
- package/src/utilities/Timer.ts +4 -4
- package/src/utilities/Utilities.ts +49 -15
- package/src/utilities/WasmMemoryManager.ts +7 -7
- package/src/utilities/WebReader.ts +23 -23
- package/src/utilities/WikipediaReader.ts +2 -2
- package/src/voice-activity-detection/AdaptiveGateVAD.ts +202 -0
- package/src/voice-activity-detection/SileroVAD.ts +5 -5
- package/src/voice-activity-detection/WebRtcVAD.ts +5 -5
- package/dist/synthesis/ElevenLabsTTS.d.ts +0 -8
- package/dist/synthesis/ElevenLabsTTS.js +0 -82
- package/dist/synthesis/ElevenLabsTTS.js.map +0 -1
- package/src/synthesis/ElevenLabsTTS.ts +0 -104
|
@@ -1,34 +1,34 @@
|
|
|
1
|
-
import { SynthesisVoice } from
|
|
2
|
-
import {
|
|
3
|
-
import { Logger } from
|
|
4
|
-
import { getRandomHexString, logToStderr, resolveModuleMainPath } from
|
|
5
|
-
import { readFile, open, close, remove, ensureDir } from
|
|
6
|
-
import path from
|
|
1
|
+
import { SynthesisVoice } from '../api/API.js'
|
|
2
|
+
import { decodeWaveToRawAudio } from '../audio/AudioUtilities.js'
|
|
3
|
+
import { Logger } from '../utilities/Logger.js'
|
|
4
|
+
import { getRandomHexString, logToStderr, resolveModuleMainPath } from '../utilities/Utilities.js'
|
|
5
|
+
import { readFile, open, close, remove, ensureDir } from '../utilities/FileSystem.js'
|
|
6
|
+
import path from 'node:path'
|
|
7
7
|
import { escape } from 'html-escaper'
|
|
8
|
-
import { getAppTempDir } from
|
|
8
|
+
import { getAppTempDir } from '../utilities/PathUtilities.js'
|
|
9
9
|
|
|
10
10
|
const log = logToStderr
|
|
11
11
|
|
|
12
|
-
export type FliteVoiceName =
|
|
12
|
+
export type FliteVoiceName = 'kal' | 'kal16' | 'awb' | 'rms' | 'slt' | string
|
|
13
13
|
|
|
14
14
|
let fliteModuleObject: WebAssembly.Module
|
|
15
15
|
|
|
16
16
|
export async function synthesize(text: string, voice: FliteVoiceName, voiceDir: string | undefined, rate: number, pitchMeanHz?: number, pitchStdDev?: number) {
|
|
17
17
|
const logger = new Logger()
|
|
18
|
-
logger.start(
|
|
18
|
+
logger.start('Get Flite WASI instance')
|
|
19
19
|
|
|
20
20
|
const randomId = getRandomHexString(16)
|
|
21
21
|
|
|
22
22
|
const outFileName = `${randomId}.out.wav`
|
|
23
23
|
const stdOutFileName = `${randomId}.stdout`
|
|
24
24
|
|
|
25
|
-
const tempDir = getAppTempDir(
|
|
25
|
+
const tempDir = getAppTempDir('flite')
|
|
26
26
|
await ensureDir(tempDir)
|
|
27
27
|
|
|
28
28
|
const tempAudioFilePath = path.join(tempDir, outFileName)
|
|
29
29
|
const tempStdOutFilePath = path.join(tempDir, stdOutFileName)
|
|
30
30
|
|
|
31
|
-
const stdOutFileFd = await open(tempStdOutFilePath,
|
|
31
|
+
const stdOutFileFd = await open(tempStdOutFilePath, 'w+')
|
|
32
32
|
|
|
33
33
|
if (voiceDir) {
|
|
34
34
|
voice = `voices/${voice}.flitevox`
|
|
@@ -85,7 +85,7 @@ export async function synthesize(text: string, voice: FliteVoiceName, voiceDir:
|
|
|
85
85
|
const moduleObject = await getModuleObject()
|
|
86
86
|
const instance = await WebAssembly.instantiate(moduleObject, importObject)
|
|
87
87
|
|
|
88
|
-
logger.start(
|
|
88
|
+
logger.start('Synthesize with flite')
|
|
89
89
|
const exitCode: number = wasi.start(instance) as any
|
|
90
90
|
|
|
91
91
|
await close(stdOutFileFd)
|
|
@@ -101,13 +101,13 @@ export async function synthesize(text: string, voice: FliteVoiceName, voiceDir:
|
|
|
101
101
|
}
|
|
102
102
|
|
|
103
103
|
const waveData = await readFile(tempAudioFilePath)
|
|
104
|
-
const stdOutString = await readFile(tempStdOutFilePath,
|
|
104
|
+
const stdOutString = await readFile(tempStdOutFilePath, 'utf8')
|
|
105
105
|
|
|
106
106
|
await cleanup()
|
|
107
107
|
|
|
108
108
|
const events = parseEventsFromTrace(stdOutString)
|
|
109
109
|
|
|
110
|
-
const { rawAudio } =
|
|
110
|
+
const { rawAudio } = decodeWaveToRawAudio(waveData)
|
|
111
111
|
|
|
112
112
|
logger.end()
|
|
113
113
|
|
|
@@ -127,7 +127,7 @@ async function getModuleObject() {
|
|
|
127
127
|
function parseEventsFromTrace(eventTrace: string) {
|
|
128
128
|
//log(eventTrace)
|
|
129
129
|
|
|
130
|
-
const eventStrings = eventTrace.trim().split(
|
|
130
|
+
const eventStrings = eventTrace.trim().split(' ')
|
|
131
131
|
const eventCount = eventStrings.length
|
|
132
132
|
|
|
133
133
|
const events: FliteEvent[] = []
|
|
@@ -135,21 +135,21 @@ function parseEventsFromTrace(eventTrace: string) {
|
|
|
135
135
|
|
|
136
136
|
for (let i = 0; i < eventCount; i++) {
|
|
137
137
|
const eventString = eventStrings[i]
|
|
138
|
-
const splitPoint = eventString.lastIndexOf(
|
|
138
|
+
const splitPoint = eventString.lastIndexOf(':')
|
|
139
139
|
|
|
140
140
|
const id = eventString.substring(0, splitPoint)
|
|
141
141
|
const startTime = events.length > 0 ? events[events.length - 1].endTime : 0
|
|
142
142
|
|
|
143
143
|
let eventType: FliteEventType
|
|
144
144
|
|
|
145
|
-
if (id ==
|
|
146
|
-
eventType =
|
|
147
|
-
} else if (id ==
|
|
148
|
-
eventType =
|
|
145
|
+
if (id == 'pau') {
|
|
146
|
+
eventType = 'pause'
|
|
147
|
+
} else if (id == '\npau') {
|
|
148
|
+
eventType = 'phrasePause'
|
|
149
149
|
|
|
150
150
|
phraseStartOffset = startTime
|
|
151
151
|
} else {
|
|
152
|
-
eventType =
|
|
152
|
+
eventType = 'phone'
|
|
153
153
|
}
|
|
154
154
|
|
|
155
155
|
const endTime = phraseStartOffset + parseFloat(eventString.substring(splitPoint + 1))
|
|
@@ -165,7 +165,7 @@ function parseEventsFromTrace(eventTrace: string) {
|
|
|
165
165
|
return events
|
|
166
166
|
}
|
|
167
167
|
|
|
168
|
-
export type FliteEventType =
|
|
168
|
+
export type FliteEventType = 'phone' | 'pause' | 'phrasePause'
|
|
169
169
|
|
|
170
170
|
export type FliteEvent = {
|
|
171
171
|
type: FliteEventType,
|
|
@@ -177,214 +177,214 @@ export type FliteEvent = {
|
|
|
177
177
|
export const voiceList: SynthesisVoice[] = [
|
|
178
178
|
// Built-in voices
|
|
179
179
|
{
|
|
180
|
-
name:
|
|
181
|
-
languages: [
|
|
182
|
-
gender:
|
|
180
|
+
name: 'slt',
|
|
181
|
+
languages: ['en-US', 'en'],
|
|
182
|
+
gender: 'female'
|
|
183
183
|
},
|
|
184
184
|
{
|
|
185
|
-
name:
|
|
186
|
-
languages: [
|
|
187
|
-
gender:
|
|
185
|
+
name: 'kal16',
|
|
186
|
+
languages: ['en-US', 'en'],
|
|
187
|
+
gender: 'male'
|
|
188
188
|
},
|
|
189
189
|
{
|
|
190
|
-
name:
|
|
191
|
-
languages: [
|
|
192
|
-
gender:
|
|
190
|
+
name: 'rms',
|
|
191
|
+
languages: ['en-US', 'en'],
|
|
192
|
+
gender: 'male'
|
|
193
193
|
},
|
|
194
194
|
{
|
|
195
|
-
name:
|
|
196
|
-
languages: [
|
|
197
|
-
gender:
|
|
195
|
+
name: 'awb',
|
|
196
|
+
languages: ['en-GB-SCOTLAND', 'en-GB', 'en'],
|
|
197
|
+
gender: 'male'
|
|
198
198
|
},
|
|
199
199
|
{
|
|
200
|
-
name:
|
|
201
|
-
languages: [
|
|
202
|
-
gender:
|
|
200
|
+
name: 'kal',
|
|
201
|
+
languages: ['en-US', 'en'],
|
|
202
|
+
gender: 'male'
|
|
203
203
|
},
|
|
204
204
|
|
|
205
205
|
|
|
206
206
|
// Voices loaded from packages
|
|
207
207
|
// US English voices
|
|
208
208
|
{
|
|
209
|
-
name:
|
|
210
|
-
languages: [
|
|
211
|
-
gender:
|
|
212
|
-
packageName:
|
|
209
|
+
name: 'cmu_us_aew',
|
|
210
|
+
languages: ['en-US', 'en'],
|
|
211
|
+
gender: 'male',
|
|
212
|
+
packageName: 'flite-cmu_us_aew'
|
|
213
213
|
},
|
|
214
214
|
{
|
|
215
|
-
name:
|
|
216
|
-
languages: [
|
|
217
|
-
gender:
|
|
218
|
-
packageName:
|
|
215
|
+
name: 'cmu_us_ahw',
|
|
216
|
+
languages: ['en-US', 'en'],
|
|
217
|
+
gender: 'male',
|
|
218
|
+
packageName: 'flite-cmu_us_ahw'
|
|
219
219
|
},
|
|
220
220
|
{
|
|
221
|
-
name:
|
|
222
|
-
languages: [
|
|
223
|
-
gender:
|
|
224
|
-
packageName:
|
|
221
|
+
name: 'cmu_us_aup',
|
|
222
|
+
languages: ['en-US', 'en'],
|
|
223
|
+
gender: 'male',
|
|
224
|
+
packageName: 'flite-cmu_us_aup'
|
|
225
225
|
},
|
|
226
226
|
{
|
|
227
|
-
name:
|
|
228
|
-
languages: [
|
|
229
|
-
gender:
|
|
230
|
-
packageName:
|
|
227
|
+
name: 'cmu_us_awb',
|
|
228
|
+
languages: ['en-US', 'en'],
|
|
229
|
+
gender: 'male',
|
|
230
|
+
packageName: 'flite-cmu_us_awb'
|
|
231
231
|
},
|
|
232
232
|
{
|
|
233
|
-
name:
|
|
234
|
-
languages: [
|
|
235
|
-
gender:
|
|
236
|
-
packageName:
|
|
233
|
+
name: 'cmu_us_axb',
|
|
234
|
+
languages: ['en-US', 'en'],
|
|
235
|
+
gender: 'female',
|
|
236
|
+
packageName: 'flite-cmu_us_axb'
|
|
237
237
|
},
|
|
238
238
|
{
|
|
239
|
-
name:
|
|
240
|
-
languages: [
|
|
241
|
-
gender:
|
|
242
|
-
packageName:
|
|
239
|
+
name: 'cmu_us_bdl',
|
|
240
|
+
languages: ['en-US', 'en'],
|
|
241
|
+
gender: 'male',
|
|
242
|
+
packageName: 'flite-cmu_us_bdl'
|
|
243
243
|
},
|
|
244
244
|
{
|
|
245
|
-
name:
|
|
246
|
-
languages: [
|
|
247
|
-
gender:
|
|
248
|
-
packageName:
|
|
245
|
+
name: 'cmu_us_clb',
|
|
246
|
+
languages: ['en-US', 'en'],
|
|
247
|
+
gender: 'female',
|
|
248
|
+
packageName: 'flite-cmu_us_clb'
|
|
249
249
|
},
|
|
250
250
|
{
|
|
251
|
-
name:
|
|
252
|
-
languages: [
|
|
253
|
-
gender:
|
|
254
|
-
packageName:
|
|
251
|
+
name: 'cmu_us_eey',
|
|
252
|
+
languages: ['en-US', 'en'],
|
|
253
|
+
gender: 'female',
|
|
254
|
+
packageName: 'flite-cmu_us_eey'
|
|
255
255
|
},
|
|
256
256
|
{
|
|
257
|
-
name:
|
|
258
|
-
languages: [
|
|
259
|
-
gender:
|
|
260
|
-
packageName:
|
|
257
|
+
name: 'cmu_us_fem',
|
|
258
|
+
languages: ['en-US', 'en'],
|
|
259
|
+
gender: 'male',
|
|
260
|
+
packageName: 'flite-cmu_us_fem'
|
|
261
261
|
},
|
|
262
262
|
{
|
|
263
|
-
name:
|
|
264
|
-
languages: [
|
|
265
|
-
gender:
|
|
266
|
-
packageName:
|
|
263
|
+
name: 'cmu_us_gka',
|
|
264
|
+
languages: ['en-US', 'en'],
|
|
265
|
+
gender: 'male',
|
|
266
|
+
packageName: 'flite-cmu_us_gka'
|
|
267
267
|
},
|
|
268
268
|
{
|
|
269
|
-
name:
|
|
270
|
-
languages: [
|
|
271
|
-
gender:
|
|
272
|
-
packageName:
|
|
269
|
+
name: 'cmu_us_jmk',
|
|
270
|
+
languages: ['en-US', 'en'],
|
|
271
|
+
gender: 'male',
|
|
272
|
+
packageName: 'flite-cmu_us_jmk'
|
|
273
273
|
},
|
|
274
274
|
{
|
|
275
|
-
name:
|
|
276
|
-
languages: [
|
|
277
|
-
gender:
|
|
278
|
-
packageName:
|
|
275
|
+
name: 'cmu_us_ksp',
|
|
276
|
+
languages: ['en-US', 'en'],
|
|
277
|
+
gender: 'male',
|
|
278
|
+
packageName: 'flite-cmu_us_ksp'
|
|
279
279
|
},
|
|
280
280
|
{
|
|
281
|
-
name:
|
|
282
|
-
languages: [
|
|
283
|
-
gender:
|
|
284
|
-
packageName:
|
|
281
|
+
name: 'cmu_us_ljm',
|
|
282
|
+
languages: ['en-US', 'en'],
|
|
283
|
+
gender: 'female',
|
|
284
|
+
packageName: 'flite-cmu_us_ljm'
|
|
285
285
|
},
|
|
286
286
|
{
|
|
287
|
-
name:
|
|
288
|
-
languages: [
|
|
289
|
-
gender:
|
|
290
|
-
packageName:
|
|
287
|
+
name: 'cmu_us_lnh',
|
|
288
|
+
languages: ['en-US', 'en'],
|
|
289
|
+
gender: 'female',
|
|
290
|
+
packageName: 'flite-cmu_us_lnh'
|
|
291
291
|
},
|
|
292
292
|
{
|
|
293
|
-
name:
|
|
294
|
-
languages: [
|
|
295
|
-
gender:
|
|
296
|
-
packageName:
|
|
293
|
+
name: 'cmu_us_rms',
|
|
294
|
+
languages: ['en-US', 'en'],
|
|
295
|
+
gender: 'male',
|
|
296
|
+
packageName: 'flite-cmu_us_rms'
|
|
297
297
|
},
|
|
298
298
|
{
|
|
299
|
-
name:
|
|
300
|
-
languages: [
|
|
301
|
-
gender:
|
|
302
|
-
packageName:
|
|
299
|
+
name: 'cmu_us_rxr',
|
|
300
|
+
languages: ['en-US', 'en'],
|
|
301
|
+
gender: 'male',
|
|
302
|
+
packageName: 'flite-cmu_us_rxr'
|
|
303
303
|
},
|
|
304
304
|
{
|
|
305
|
-
name:
|
|
306
|
-
languages: [
|
|
307
|
-
gender:
|
|
308
|
-
packageName:
|
|
305
|
+
name: 'cmu_us_slp',
|
|
306
|
+
languages: ['en-US', 'en'],
|
|
307
|
+
gender: 'female',
|
|
308
|
+
packageName: 'flite-cmu_us_slp'
|
|
309
309
|
},
|
|
310
310
|
{
|
|
311
|
-
name:
|
|
312
|
-
languages: [
|
|
313
|
-
gender:
|
|
314
|
-
packageName:
|
|
311
|
+
name: 'cmu_us_slt',
|
|
312
|
+
languages: ['en-US', 'en'],
|
|
313
|
+
gender: 'female',
|
|
314
|
+
packageName: 'flite-cmu_us_slt'
|
|
315
315
|
},
|
|
316
316
|
|
|
317
317
|
// Indic voices
|
|
318
318
|
{
|
|
319
|
-
name:
|
|
320
|
-
languages: [
|
|
321
|
-
gender:
|
|
322
|
-
packageName:
|
|
319
|
+
name: 'cmu_indic_ben_rm',
|
|
320
|
+
languages: ['be', 'bn'],// Bengali
|
|
321
|
+
gender: 'female',
|
|
322
|
+
packageName: 'flite-cmu_indic_ben_rm'
|
|
323
323
|
},
|
|
324
324
|
{
|
|
325
|
-
name:
|
|
326
|
-
languages: [
|
|
327
|
-
gender:
|
|
328
|
-
packageName:
|
|
325
|
+
name: 'cmu_indic_guj_ad',
|
|
326
|
+
languages: ['gu'],// Gujarati
|
|
327
|
+
gender: 'male',
|
|
328
|
+
packageName: 'flite-cmu_indic_guj_ad'
|
|
329
329
|
},
|
|
330
330
|
{
|
|
331
|
-
name:
|
|
332
|
-
languages: [
|
|
333
|
-
gender:
|
|
334
|
-
packageName:
|
|
331
|
+
name: 'cmu_indic_guj_dp',
|
|
332
|
+
languages: ['gu'],// Gujarati
|
|
333
|
+
gender: 'female',
|
|
334
|
+
packageName: 'flite-cmu_indic_guj_dp'
|
|
335
335
|
},
|
|
336
336
|
{
|
|
337
|
-
name:
|
|
338
|
-
languages: [
|
|
339
|
-
gender:
|
|
340
|
-
packageName:
|
|
337
|
+
name: 'cmu_indic_guj_kt',
|
|
338
|
+
languages: ['gu'],// Gujarati
|
|
339
|
+
gender: 'female',
|
|
340
|
+
packageName: 'flite-cmu_indic_guj_kt'
|
|
341
341
|
},
|
|
342
342
|
{
|
|
343
|
-
name:
|
|
344
|
-
languages: [
|
|
345
|
-
gender:
|
|
346
|
-
packageName:
|
|
343
|
+
name: 'cmu_indic_hin_ab',
|
|
344
|
+
languages: ['hi'],// Hindi
|
|
345
|
+
gender: 'female',
|
|
346
|
+
packageName: 'flite-cmu_indic_hin_ab'
|
|
347
347
|
},
|
|
348
348
|
{
|
|
349
|
-
name:
|
|
350
|
-
languages: [
|
|
351
|
-
gender:
|
|
352
|
-
packageName:
|
|
349
|
+
name: 'cmu_indic_kan_plv',
|
|
350
|
+
languages: ['ka'],// Kannada
|
|
351
|
+
gender: 'female',
|
|
352
|
+
packageName: 'flite-cmu_indic_kan_plv'
|
|
353
353
|
},
|
|
354
354
|
{
|
|
355
|
-
name:
|
|
356
|
-
languages: [
|
|
357
|
-
gender:
|
|
358
|
-
packageName:
|
|
355
|
+
name: 'cmu_indic_mar_aup',
|
|
356
|
+
languages: ['mr'],// Marathi
|
|
357
|
+
gender: 'male',
|
|
358
|
+
packageName: 'flite-cmu_indic_mar_aup'
|
|
359
359
|
},
|
|
360
360
|
{
|
|
361
|
-
name:
|
|
362
|
-
languages: [
|
|
363
|
-
gender:
|
|
364
|
-
packageName:
|
|
361
|
+
name: 'cmu_indic_mar_slp',
|
|
362
|
+
languages: ['mr'],// Marathi
|
|
363
|
+
gender: 'female',
|
|
364
|
+
packageName: 'flite-cmu_indic_mar_slp'
|
|
365
365
|
},
|
|
366
366
|
{
|
|
367
|
-
name:
|
|
368
|
-
languages: [
|
|
369
|
-
gender:
|
|
370
|
-
packageName:
|
|
367
|
+
name: 'cmu_indic_pan_amp',
|
|
368
|
+
languages: ['pa'],// Punjabi
|
|
369
|
+
gender: 'female',
|
|
370
|
+
packageName: 'flite-cmu_indic_pan_amp'
|
|
371
371
|
},
|
|
372
372
|
{
|
|
373
|
-
name:
|
|
374
|
-
languages: [
|
|
375
|
-
gender:
|
|
376
|
-
packageName:
|
|
373
|
+
name: 'cmu_indic_tel_kpn',
|
|
374
|
+
languages: ['te'],// Telugu
|
|
375
|
+
gender: 'female',
|
|
376
|
+
packageName: 'flite-cmu_indic_tel_kpn'
|
|
377
377
|
},
|
|
378
378
|
{
|
|
379
|
-
name:
|
|
380
|
-
languages: [
|
|
381
|
-
gender:
|
|
382
|
-
packageName:
|
|
379
|
+
name: 'cmu_indic_tel_sk',
|
|
380
|
+
languages: ['te'],// Telugu
|
|
381
|
+
gender: 'male',
|
|
382
|
+
packageName: 'flite-cmu_indic_tel_sk'
|
|
383
383
|
},
|
|
384
384
|
{
|
|
385
|
-
name:
|
|
386
|
-
languages: [
|
|
387
|
-
gender:
|
|
388
|
-
packageName:
|
|
385
|
+
name: 'cmu_indic_tel_ss',
|
|
386
|
+
languages: ['te'],// Telugu
|
|
387
|
+
gender: 'female',
|
|
388
|
+
packageName: 'flite-cmu_indic_tel_ss'
|
|
389
389
|
},
|
|
390
390
|
]
|
|
@@ -1,12 +1,12 @@
|
|
|
1
|
-
import { request } from
|
|
2
|
-
import { Logger } from
|
|
3
|
-
import { logToStderr } from
|
|
1
|
+
import { request } from 'gaxios'
|
|
2
|
+
import { Logger } from '../utilities/Logger.js'
|
|
3
|
+
import { logToStderr } from '../utilities/Utilities.js'
|
|
4
4
|
|
|
5
5
|
const log = logToStderr
|
|
6
6
|
|
|
7
|
-
export async function synthesize(text: string, apiKey: string, languageCode =
|
|
7
|
+
export async function synthesize(text: string, apiKey: string, languageCode = 'en-US', voice = 'en-US-Wavenet-C', speakingRate = 1.0, pitchDeltaSemitones = 0.0, volumeGainDecibels = 0.0, ssml = false, audioEncoding: AudioEncoding = 'MP3_64_KBPS', sampleRate = 24000) {
|
|
8
8
|
const logger = new Logger()
|
|
9
|
-
logger.start(
|
|
9
|
+
logger.start('Request synthesis from Google Cloud')
|
|
10
10
|
|
|
11
11
|
const requestBody = {
|
|
12
12
|
input: {
|
|
@@ -23,11 +23,11 @@ export async function synthesize(text: string, apiKey: string, languageCode = "e
|
|
|
23
23
|
audioEncoding,
|
|
24
24
|
speakingRate,
|
|
25
25
|
pitch: pitchDeltaSemitones,
|
|
26
|
-
volumeGainDb,
|
|
26
|
+
volumeGainDb: volumeGainDecibels,
|
|
27
27
|
sampleRateHertz: sampleRate
|
|
28
28
|
},
|
|
29
29
|
|
|
30
|
-
enableTimePointing: [
|
|
30
|
+
enableTimePointing: ['SSML_MARK']
|
|
31
31
|
}
|
|
32
32
|
|
|
33
33
|
if (ssml) {
|
|
@@ -37,24 +37,24 @@ export async function synthesize(text: string, apiKey: string, languageCode = "e
|
|
|
37
37
|
}
|
|
38
38
|
|
|
39
39
|
const response = await request<any>({
|
|
40
|
-
method:
|
|
40
|
+
method: 'POST',
|
|
41
41
|
|
|
42
42
|
url: `https://texttospeech.googleapis.com/v1beta1/text:synthesize`,
|
|
43
43
|
|
|
44
44
|
params: {
|
|
45
|
-
|
|
45
|
+
'key': apiKey
|
|
46
46
|
},
|
|
47
47
|
|
|
48
48
|
headers: {
|
|
49
|
-
|
|
49
|
+
'User-Agent': ''
|
|
50
50
|
},
|
|
51
51
|
|
|
52
52
|
data: requestBody,
|
|
53
53
|
|
|
54
|
-
responseType:
|
|
54
|
+
responseType: 'json'
|
|
55
55
|
})
|
|
56
56
|
|
|
57
|
-
logger.start(
|
|
57
|
+
logger.start('Parse result')
|
|
58
58
|
|
|
59
59
|
const result = parseResponseBody(response.data)
|
|
60
60
|
|
|
@@ -64,7 +64,7 @@ export async function synthesize(text: string, apiKey: string, languageCode = "e
|
|
|
64
64
|
}
|
|
65
65
|
|
|
66
66
|
function parseResponseBody(responseBody: any) {
|
|
67
|
-
const audioData = Buffer.from(responseBody.audioContent,
|
|
67
|
+
const audioData = Buffer.from(responseBody.audioContent, 'base64')
|
|
68
68
|
const timepoints: timePoint[] = responseBody.timepoints
|
|
69
69
|
|
|
70
70
|
return { audioData, timepoints }
|
|
@@ -75,19 +75,19 @@ export async function getVoiceList(apiKey: string) {
|
|
|
75
75
|
const requestURL = `https://texttospeech.googleapis.com/v1beta1/voices`
|
|
76
76
|
|
|
77
77
|
const response = await request<any>({
|
|
78
|
-
method:
|
|
78
|
+
method: 'GET',
|
|
79
79
|
|
|
80
80
|
url: requestURL,
|
|
81
81
|
|
|
82
82
|
params: {
|
|
83
|
-
|
|
83
|
+
'key': apiKey
|
|
84
84
|
},
|
|
85
85
|
|
|
86
86
|
headers: {
|
|
87
|
-
|
|
87
|
+
'User-Agent': ''
|
|
88
88
|
},
|
|
89
89
|
|
|
90
|
-
responseType:
|
|
90
|
+
responseType: 'json'
|
|
91
91
|
})
|
|
92
92
|
|
|
93
93
|
const responseData = response.data
|
|
@@ -100,11 +100,11 @@ export async function getVoiceList(apiKey: string) {
|
|
|
100
100
|
export type GoogleCloudVoice = {
|
|
101
101
|
name: string
|
|
102
102
|
languageCodes: string[]
|
|
103
|
-
ssmlGender:
|
|
103
|
+
ssmlGender: 'MALE' | 'FEMALE'
|
|
104
104
|
naturalSampleRateHertz: number
|
|
105
105
|
}
|
|
106
106
|
|
|
107
|
-
export type AudioEncoding =
|
|
107
|
+
export type AudioEncoding = 'LINEAR16' | 'MP3' | 'MP3_64_KBPS' | 'OGG_OPUS' | 'MULAW' | 'ALAW'
|
|
108
108
|
|
|
109
109
|
export type timePoint = {
|
|
110
110
|
markName: string,
|