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
|
@@ -1,8 +0,0 @@
|
|
|
1
|
-
import { SynthesisVoice } from "../api/API.js";
|
|
2
|
-
export declare function synthesize(text: string, voiceId: string, apiKey: string, modelId: string, stability?: number, similarityBoost?: number): Promise<{
|
|
3
|
-
rawAudio: {
|
|
4
|
-
audioChannels: Float32Array[];
|
|
5
|
-
sampleRate: number;
|
|
6
|
-
};
|
|
7
|
-
}>;
|
|
8
|
-
export declare function getVoiceList(apiKey: string): Promise<SynthesisVoice[]>;
|
|
@@ -1,82 +0,0 @@
|
|
|
1
|
-
import { request } from "gaxios";
|
|
2
|
-
import * as FFMpegTranscoder from "../codecs/FFMpegTranscoder.js";
|
|
3
|
-
import { Logger } from "../utilities/Logger.js";
|
|
4
|
-
import { logToStderr } from "../utilities/Utilities.js";
|
|
5
|
-
const log = logToStderr;
|
|
6
|
-
export async function synthesize(text, voiceId, apiKey, modelId, stability = 0, similarityBoost = 0) {
|
|
7
|
-
const logger = new Logger();
|
|
8
|
-
logger.start("Request synthesis from ElevenLabs");
|
|
9
|
-
let response;
|
|
10
|
-
try {
|
|
11
|
-
response = await request({
|
|
12
|
-
url: `https://api.elevenlabs.io/v1/text-to-speech/${voiceId}`,
|
|
13
|
-
method: "POST",
|
|
14
|
-
headers: {
|
|
15
|
-
"accept": "audio/mpeg",
|
|
16
|
-
"xi-api-key": apiKey,
|
|
17
|
-
},
|
|
18
|
-
data: {
|
|
19
|
-
text,
|
|
20
|
-
model_id: modelId,
|
|
21
|
-
voice_setting: {
|
|
22
|
-
stability,
|
|
23
|
-
similarity_boost: similarityBoost
|
|
24
|
-
}
|
|
25
|
-
},
|
|
26
|
-
responseType: "arraybuffer"
|
|
27
|
-
});
|
|
28
|
-
}
|
|
29
|
-
catch (e) {
|
|
30
|
-
const response = e.response;
|
|
31
|
-
if (response) {
|
|
32
|
-
logger.log(`Request failed with status code ${response.status}`);
|
|
33
|
-
if (response.data) {
|
|
34
|
-
logger.log(`Server responded with:`);
|
|
35
|
-
logger.log(response.data);
|
|
36
|
-
}
|
|
37
|
-
}
|
|
38
|
-
throw e;
|
|
39
|
-
}
|
|
40
|
-
logger.start("Decode synthesized audio");
|
|
41
|
-
const rawAudio = await FFMpegTranscoder.decodeToChannels(Buffer.from(response.data));
|
|
42
|
-
logger.end();
|
|
43
|
-
return { rawAudio };
|
|
44
|
-
}
|
|
45
|
-
export async function getVoiceList(apiKey) {
|
|
46
|
-
const response = await request({
|
|
47
|
-
method: "GET",
|
|
48
|
-
url: "https://api.elevenlabs.io/v1/voices",
|
|
49
|
-
headers: {
|
|
50
|
-
"accept": "accept: application/json",
|
|
51
|
-
"xi-api-key": apiKey
|
|
52
|
-
},
|
|
53
|
-
responseType: "json"
|
|
54
|
-
});
|
|
55
|
-
const elevenLabsVoices = response.data.voices;
|
|
56
|
-
const voices = elevenLabsVoices.map(elevenLabsVoice => {
|
|
57
|
-
const accent = elevenLabsVoice?.labels?.accent;
|
|
58
|
-
const gender = elevenLabsVoice?.labels?.gender || "unknown";
|
|
59
|
-
let language;
|
|
60
|
-
if (!accent || accent.startsWith("american")) {
|
|
61
|
-
language = 'en-US';
|
|
62
|
-
}
|
|
63
|
-
else if (accent.startsWith("british") || accent == "irish") {
|
|
64
|
-
language = 'en-GB';
|
|
65
|
-
}
|
|
66
|
-
else if (accent == "australian") {
|
|
67
|
-
language = 'en-AU';
|
|
68
|
-
}
|
|
69
|
-
else {
|
|
70
|
-
language = 'en-US';
|
|
71
|
-
}
|
|
72
|
-
return {
|
|
73
|
-
name: elevenLabsVoice.name,
|
|
74
|
-
languages: [language, 'en'],
|
|
75
|
-
gender,
|
|
76
|
-
elevenLabsVoiceId: elevenLabsVoice.voice_id,
|
|
77
|
-
elevenLabsModelId: elevenLabsVoice?.high_quality_base_model_ids?.[0] || 'eleven_monolingual_v1'
|
|
78
|
-
};
|
|
79
|
-
});
|
|
80
|
-
return voices;
|
|
81
|
-
}
|
|
82
|
-
//# sourceMappingURL=ElevenLabsTTS.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"ElevenLabsTTS.js","sourceRoot":"","sources":["../../src/synthesis/ElevenLabsTTS.ts"],"names":[],"mappings":"AAAA,OAAO,EAAkB,OAAO,EAAE,MAAM,QAAQ,CAAA;AAEhD,OAAO,KAAK,gBAAgB,MAAM,+BAA+B,CAAA;AACjE,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAC/C,OAAO,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAA;AAEvD,MAAM,GAAG,GAAG,WAAW,CAAA;AAEvB,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,IAAY,EAAE,OAAe,EAAE,MAAc,EAAE,OAAe,EAAE,SAAS,GAAG,CAAC,EAAE,eAAe,GAAG,CAAC;IAClI,MAAM,MAAM,GAAG,IAAI,MAAM,EAAE,CAAA;IAC3B,MAAM,CAAC,KAAK,CAAC,mCAAmC,CAAC,CAAA;IAEjD,IAAI,QAA6B,CAAA;IAEjC,IAAI,CAAC;QACJ,QAAQ,GAAG,MAAM,OAAO,CAAM;YAC7B,GAAG,EAAE,+CAA+C,OAAO,EAAE;YAE7D,MAAM,EAAE,MAAM;YAEd,OAAO,EAAE;gBACR,QAAQ,EAAE,YAAY;gBACtB,YAAY,EAAE,MAAM;aACpB;YAED,IAAI,EAAE;gBACL,IAAI;gBAEJ,QAAQ,EAAE,OAAO;gBAEjB,aAAa,EAAE;oBACd,SAAS;oBACT,gBAAgB,EAAE,eAAe;iBACjC;aACD;YAED,YAAY,EAAE,aAAa;SAC3B,CAAC,CAAA;IACH,CAAC;IAAC,OAAO,CAAM,EAAE,CAAC;QACjB,MAAM,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAA;QAE3B,IAAI,QAAQ,EAAE,CAAC;YACd,MAAM,CAAC,GAAG,CAAC,mCAAmC,QAAQ,CAAC,MAAM,EAAE,CAAC,CAAA;YAEhE,IAAI,QAAQ,CAAC,IAAI,EAAE,CAAC;gBACnB,MAAM,CAAC,GAAG,CAAC,wBAAwB,CAAC,CAAA;gBACpC,MAAM,CAAC,GAAG,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAA;YAC1B,CAAC;QACF,CAAC;QAED,MAAM,CAAC,CAAA;IACR,CAAC;IAED,MAAM,CAAC,KAAK,CAAC,0BAA0B,CAAC,CAAA;IACxC,MAAM,QAAQ,GAAG,MAAM,gBAAgB,CAAC,gBAAgB,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAA;IAEpF,MAAM,CAAC,GAAG,EAAE,CAAA;IAEZ,OAAO,EAAE,QAAQ,EAAE,CAAA;AACpB,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,YAAY,CAAC,MAAc;IAChD,MAAM,QAAQ,GAAG,MAAM,OAAO,CAAM;QACnC,MAAM,EAAE,KAAK;QAEb,GAAG,EAAE,qCAAqC;QAE1C,OAAO,EAAE;YACR,QAAQ,EAAE,0BAA0B;YACpC,YAAY,EAAE,MAAM;SACpB;QAED,YAAY,EAAE,MAAM;KACpB,CAAC,CAAA;IAEF,MAAM,gBAAgB,GAAU,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAA;IAEpD,MAAM,MAAM,GAAqB,gBAAgB,CAAC,GAAG,CAAC,eAAe,CAAC,EAAE;QACvE,MAAM,MAAM,GAAuB,eAAe,EAAE,MAAM,EAAE,MAAM,CAAA;QAClE,MAAM,MAAM,GAAgB,eAAe,EAAE,MAAM,EAAE,MAAM,IAAI,SAAS,CAAA;QAExE,IAAI,QAAgB,CAAA;QAEpB,IAAI,CAAC,MAAM,IAAI,MAAM,CAAC,UAAU,CAAC,UAAU,CAAC,EAAE,CAAC;YAC9C,QAAQ,GAAG,OAAO,CAAA;QACnB,CAAC;aAAM,IAAI,MAAM,CAAC,UAAU,CAAC,SAAS,CAAC,IAAI,MAAM,IAAI,OAAO,EAAE,CAAC;YAC9D,QAAQ,GAAG,OAAO,CAAA;QACnB,CAAC;aAAM,IAAI,MAAM,IAAI,YAAY,EAAE,CAAC;YACnC,QAAQ,GAAG,OAAO,CAAA;QACnB,CAAC;aAAM,CAAC;YACP,QAAQ,GAAG,OAAO,CAAA;QACnB,CAAC;QAED,OAAO;YACN,IAAI,EAAE,eAAe,CAAC,IAAI;YAC1B,SAAS,EAAE,CAAC,QAAQ,EAAE,IAAI,CAAC;YAC3B,MAAM;YAEN,iBAAiB,EAAE,eAAe,CAAC,QAAQ;YAC3C,iBAAiB,EAAE,eAAe,EAAE,2BAA2B,EAAE,CAAC,CAAC,CAAC,IAAI,uBAAuB;SAC/F,CAAA;IAAA,CAAC,CAAC,CAAA;IAEJ,OAAO,MAAM,CAAA;AACd,CAAC"}
|
|
@@ -1,104 +0,0 @@
|
|
|
1
|
-
import { GaxiosResponse, request } from "gaxios"
|
|
2
|
-
import { SynthesisVoice, VoiceGender } from "../api/API.js"
|
|
3
|
-
import * as FFMpegTranscoder from "../codecs/FFMpegTranscoder.js"
|
|
4
|
-
import { Logger } from "../utilities/Logger.js"
|
|
5
|
-
import { logToStderr } from "../utilities/Utilities.js"
|
|
6
|
-
|
|
7
|
-
const log = logToStderr
|
|
8
|
-
|
|
9
|
-
export async function synthesize(text: string, voiceId: string, apiKey: string, modelId: string, stability = 0, similarityBoost = 0) {
|
|
10
|
-
const logger = new Logger()
|
|
11
|
-
logger.start("Request synthesis from ElevenLabs")
|
|
12
|
-
|
|
13
|
-
let response: GaxiosResponse<any>
|
|
14
|
-
|
|
15
|
-
try {
|
|
16
|
-
response = await request<any>({
|
|
17
|
-
url: `https://api.elevenlabs.io/v1/text-to-speech/${voiceId}`,
|
|
18
|
-
|
|
19
|
-
method: "POST",
|
|
20
|
-
|
|
21
|
-
headers: {
|
|
22
|
-
"accept": "audio/mpeg",
|
|
23
|
-
"xi-api-key": apiKey,
|
|
24
|
-
},
|
|
25
|
-
|
|
26
|
-
data: {
|
|
27
|
-
text,
|
|
28
|
-
|
|
29
|
-
model_id: modelId,
|
|
30
|
-
|
|
31
|
-
voice_setting: {
|
|
32
|
-
stability,
|
|
33
|
-
similarity_boost: similarityBoost
|
|
34
|
-
}
|
|
35
|
-
},
|
|
36
|
-
|
|
37
|
-
responseType: "arraybuffer"
|
|
38
|
-
})
|
|
39
|
-
} catch (e: any) {
|
|
40
|
-
const response = e.response
|
|
41
|
-
|
|
42
|
-
if (response) {
|
|
43
|
-
logger.log(`Request failed with status code ${response.status}`)
|
|
44
|
-
|
|
45
|
-
if (response.data) {
|
|
46
|
-
logger.log(`Server responded with:`)
|
|
47
|
-
logger.log(response.data)
|
|
48
|
-
}
|
|
49
|
-
}
|
|
50
|
-
|
|
51
|
-
throw e
|
|
52
|
-
}
|
|
53
|
-
|
|
54
|
-
logger.start("Decode synthesized audio")
|
|
55
|
-
const rawAudio = await FFMpegTranscoder.decodeToChannels(Buffer.from(response.data))
|
|
56
|
-
|
|
57
|
-
logger.end()
|
|
58
|
-
|
|
59
|
-
return { rawAudio }
|
|
60
|
-
}
|
|
61
|
-
|
|
62
|
-
export async function getVoiceList(apiKey: string) {
|
|
63
|
-
const response = await request<any>({
|
|
64
|
-
method: "GET",
|
|
65
|
-
|
|
66
|
-
url: "https://api.elevenlabs.io/v1/voices",
|
|
67
|
-
|
|
68
|
-
headers: {
|
|
69
|
-
"accept": "accept: application/json",
|
|
70
|
-
"xi-api-key": apiKey
|
|
71
|
-
},
|
|
72
|
-
|
|
73
|
-
responseType: "json"
|
|
74
|
-
})
|
|
75
|
-
|
|
76
|
-
const elevenLabsVoices: any[] = response.data.voices
|
|
77
|
-
|
|
78
|
-
const voices: SynthesisVoice[] = elevenLabsVoices.map(elevenLabsVoice => {
|
|
79
|
-
const accent: string | undefined = elevenLabsVoice?.labels?.accent
|
|
80
|
-
const gender: VoiceGender = elevenLabsVoice?.labels?.gender || "unknown"
|
|
81
|
-
|
|
82
|
-
let language: string
|
|
83
|
-
|
|
84
|
-
if (!accent || accent.startsWith("american")) {
|
|
85
|
-
language = 'en-US'
|
|
86
|
-
} else if (accent.startsWith("british") || accent == "irish") {
|
|
87
|
-
language = 'en-GB'
|
|
88
|
-
} else if (accent == "australian") {
|
|
89
|
-
language = 'en-AU'
|
|
90
|
-
} else {
|
|
91
|
-
language = 'en-US'
|
|
92
|
-
}
|
|
93
|
-
|
|
94
|
-
return {
|
|
95
|
-
name: elevenLabsVoice.name,
|
|
96
|
-
languages: [language, 'en'],
|
|
97
|
-
gender,
|
|
98
|
-
|
|
99
|
-
elevenLabsVoiceId: elevenLabsVoice.voice_id,
|
|
100
|
-
elevenLabsModelId: elevenLabsVoice?.high_quality_base_model_ids?.[0] || 'eleven_monolingual_v1'
|
|
101
|
-
}})
|
|
102
|
-
|
|
103
|
-
return voices
|
|
104
|
-
}
|