@qvac/sdk 0.8.0 → 1.0.0

package/dist/examples/transcription/parakeet-sortformer.js

@@ -1,115 +0,0 @@
-import { loadModel, unloadModel, transcribe, PARAKEET_TDT_ENCODER_FP32, PARAKEET_TDT_ENCODER_DATA_FP32, PARAKEET_TDT_DECODER_FP32, PARAKEET_TDT_VOCAB, PARAKEET_TDT_PREPROCESSOR_FP32, PARAKEET_SORTFORMER_FP32, } from "@qvac/sdk";
-import { dirname, join } from "path";
-import { fileURLToPath } from "url";
-import { readFileSync, writeFileSync, mkdirSync } from "fs";
-import { tmpdir } from "os";
-const __dirname = dirname(fileURLToPath(import.meta.url));
-const args = process.argv.slice(2);
-const sortformerSrc = args[0] ?? PARAKEET_SORTFORMER_FP32;
-const defaultAudioPath = join(__dirname, "..", "..", "..", "examples", "transcription", "audio", "diarization-sample-16k.wav");
-const audioFilePath = args[1] ?? defaultAudioPath;
-// ── Step 1: Diarize with Sortformer ──
-const sfModelId = await loadModel({
-    modelSrc: sortformerSrc,
-    modelType: "parakeet",
-    modelConfig: {
-        modelType: "sortformer",
-        parakeetSortformerSrc: sortformerSrc,
-    },
-});
-const diarization = await transcribe({
-    modelId: sfModelId,
-    audioChunk: audioFilePath,
-});
-await unloadModel({ modelId: sfModelId });
-const segments = parseDiarization(diarization);
-// ── Step 2: Transcribe each segment with TDT ──
-const tdtModelId = await loadModel({
-    modelSrc: PARAKEET_TDT_ENCODER_FP32,
-    modelType: "parakeet",
-    modelConfig: {
-        parakeetEncoderSrc: PARAKEET_TDT_ENCODER_FP32,
-        parakeetEncoderDataSrc: PARAKEET_TDT_ENCODER_DATA_FP32,
-        parakeetDecoderSrc: PARAKEET_TDT_DECODER_FP32,
-        parakeetVocabSrc: PARAKEET_TDT_VOCAB,
-        parakeetPreprocessorSrc: PARAKEET_TDT_PREPROCESSOR_FP32,
-    },
-});
-const pcm = readPcm(audioFilePath);
-const sliceDir = join(tmpdir(), `qvac-diarize-${Date.now()}`);
-mkdirSync(sliceDir, { recursive: true });
-const results = [];
-for (let i = 0; i < segments.length; i++) {
-    const seg = segments[i];
-    const slicePath = join(sliceDir, `seg-${i}.wav`);
-    if (!writeWavSlice(pcm, seg.start, seg.end, slicePath)) {
-        results.push({ ...seg, text: "[No speech detected]" });
-        continue;
-    }
-    const text = await transcribe({ modelId: tdtModelId, audioChunk: slicePath });
-    results.push({ ...seg, text: text.trim() || "[No speech detected]" });
-}
-await unloadModel({ modelId: tdtModelId });
-// ── Step 3: Merge consecutive same-speaker segments and print ──
-const merged = mergeSpeakers(results);
-console.log("\n=== DIARIZED TRANSCRIPTION ===");
-console.log("=".repeat(60));
-for (const entry of merged) {
-    console.log(`Speaker ${entry.speaker} (${entry.start.toFixed(2)}s - ${entry.end.toFixed(2)}s):`);
-    console.log(`  ${entry.text}\n`);
-}
-console.log("=".repeat(60));
-console.log("\nDone!");
-// ── Helpers ──
-function parseDiarization(text) {
-    const segs = [];
-    for (const line of text.split("\n")) {
-        const m = line.match(/Speaker (\d+): ([\d.]+)s - ([\d.]+)s/);
-        if (m)
-            segs.push({ speaker: +m[1], start: +m[2], end: +m[3] });
-    }
-    return segs.sort((a, b) => a.start - b.start);
-}
-function readPcm(wavPath) {
-    const buf = readFileSync(wavPath);
-    const dataOffset = buf.indexOf("data") + 4;
-    return buf.subarray(dataOffset + 4, dataOffset + 4 + buf.readUInt32LE(dataOffset));
-}
-function writeWavSlice(pcm, startSec, endSec, outPath) {
-    const SR = 16000;
-    const BPS = 2;
-    const startByte = Math.floor(startSec * SR) * BPS;
-    const endByte = Math.min(Math.ceil(endSec * SR) * BPS, pcm.length);
-    if (startByte >= endByte)
-        return false;
-    const slice = pcm.subarray(startByte, endByte);
-    const hdr = Buffer.alloc(44);
-    hdr.write("RIFF", 0);
-    hdr.writeUInt32LE(36 + slice.length, 4);
-    hdr.write("WAVEfmt ", 8);
-    hdr.writeUInt32LE(16, 16);
-    hdr.writeUInt16LE(1, 20);
-    hdr.writeUInt16LE(1, 22);
-    hdr.writeUInt32LE(SR, 24);
-    hdr.writeUInt32LE(SR * BPS, 28);
-    hdr.writeUInt16LE(BPS, 32);
-    hdr.writeUInt16LE(16, 34);
-    hdr.write("data", 36);
-    hdr.writeUInt32LE(slice.length, 40);
-    writeFileSync(outPath, Buffer.concat([hdr, slice]));
-    return true;
-}
-function mergeSpeakers(entries) {
-    const out = [];
-    for (const e of entries) {
-        const last = out[out.length - 1];
-        if (last && last.speaker === e.speaker) {
-            last.text += " " + e.text;
-            last.end = e.end;
-        }
-        else {
-            out.push({ ...e });
-        }
-    }
-    return out;
-}

package/dist/examples/transcription/parakeet-tdt-filesystem.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=parakeet-tdt-filesystem.d.ts.map

package/dist/examples/transcription/parakeet-tdt-filesystem.js

@@ -1,44 +0,0 @@
-import { loadModel, unloadModel, transcribe, PARAKEET_TDT_ENCODER_FP32, PARAKEET_TDT_ENCODER_DATA_FP32, PARAKEET_TDT_DECODER_FP32, PARAKEET_TDT_VOCAB, PARAKEET_TDT_PREPROCESSOR_FP32, } from "@qvac/sdk";
-const args = process.argv.slice(2);
-if (!args[0]) {
-    console.error("Usage: bun run examples/transcription/parakeet-tdt-filesystem.ts <wav-file-path> " +
-        "[encoder-onnx] [encoder-data] [decoder-onnx] [vocab-txt] [preprocessor-onnx]");
-    console.error("\nIf model paths are omitted, defaults to registry models.");
-    process.exit(1);
-}
-const audioFilePath = args[0];
-const parakeetEncoderSrc = args[1] ?? PARAKEET_TDT_ENCODER_FP32;
-const parakeetEncoderDataSrc = args[2] ?? PARAKEET_TDT_ENCODER_DATA_FP32;
-const parakeetDecoderSrc = args[3] ?? PARAKEET_TDT_DECODER_FP32;
-const parakeetVocabSrc = args[4] ?? PARAKEET_TDT_VOCAB;
-const parakeetPreprocessorSrc = args[5] ?? PARAKEET_TDT_PREPROCESSOR_FP32;
-try {
-    console.log("Starting Parakeet transcription example...");
-    console.log("Loading Parakeet model...");
-    const modelId = await loadModel({
-        modelSrc: parakeetEncoderSrc,
-        modelType: "parakeet",
-        modelConfig: {
-            parakeetEncoderSrc,
-            parakeetEncoderDataSrc,
-            parakeetDecoderSrc,
-            parakeetVocabSrc,
-            parakeetPreprocessorSrc,
-        },
-        onProgress: (progress) => {
-            console.log(`Download progress: ${progress.percentage.toFixed(1)}%`);
-        },
-    });
-    console.log(`Parakeet model loaded with ID: ${modelId}`);
-    console.log("Transcribing audio...");
-    const text = await transcribe({ modelId, audioChunk: audioFilePath });
-    console.log("Transcription result:");
-    console.log(text);
-    console.log("Unloading Parakeet model...");
-    await unloadModel({ modelId });
-    console.log("Parakeet model unloaded successfully");
-}
-catch (error) {
-    console.error("Error:", error);
-    process.exit(1);
-}

package/dist/examples/transcription/whispercpp-filesystem.js

@@ -1,69 +0,0 @@
-import { loadModel, unloadModel, transcribe, WHISPER_TINY } from "@qvac/sdk";
-// Parse command line arguments
-const args = process.argv.slice(2);
-if (!args[0]) {
-    console.error("Usage: bun run examples/whispercpp-filesystem.ts <wav-file-path>");
-    process.exit(1);
-}
-const audioFilePath = args[0];
-try {
-    console.log("🎤 Starting Whisper transcription example...");
-    // Load the Whisper model
-    console.log("📥 Loading Whisper model...");
-    const modelId = await loadModel({
-        modelSrc: WHISPER_TINY,
-        modelType: "whisper",
-        modelConfig: {
-            audio_format: "f32le",
-            // Sampling strategy
-            strategy: "greedy",
-            n_threads: 4,
-            // Transcription options
-            language: "en",
-            translate: false,
-            no_timestamps: false,
-            single_segment: false,
-            print_timestamps: true,
-            token_timestamps: true,
-            // Quality settings
-            temperature: 0.0,
-            suppress_blank: true,
-            suppress_nst: true,
-            // Advanced tuning
-            entropy_thold: 2.4,
-            logprob_thold: -1.0,
-            // VAD configuration
-            vad_params: {
-                threshold: 0.35,
-                min_speech_duration_ms: 200,
-                min_silence_duration_ms: 150,
-                max_speech_duration_s: 30.0,
-                speech_pad_ms: 600,
-                samples_overlap: 0.3,
-            },
-            // Context parameters for GPU
-            contextParams: {
-                use_gpu: true,
-                flash_attn: true,
-                gpu_device: 0,
-            },
-        },
-        onProgress: (progress) => {
-            console.log(progress);
-        },
-    });
-    console.log(`✅ Whisper model loaded with ID: ${modelId}`);
-    // Perform transcription
-    console.log("🎧 Transcribing audio...");
-    const text = await transcribe({ modelId, audioChunk: audioFilePath });
-    console.log("📝 Transcription result:");
-    console.log(text);
-    // Unload the model when done
-    console.log("🧹 Unloading Whisper model...");
-    await unloadModel({ modelId });
-    console.log("✅ Whisper model unloaded successfully");
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/transcription/whispercpp-prompt.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=whispercpp-prompt.d.ts.map

package/dist/examples/transcription/whispercpp-prompt.js

@@ -1,67 +0,0 @@
-import { loadModel, unloadModel, transcribe, WHISPER_TINY } from "@qvac/sdk";
-try {
-    console.log("🎤 Starting Whisper transcription with prompt example...");
-    // Load the Whisper model
-    console.log("📥 Loading Whisper model...");
-    const modelId = await loadModel({
-        modelSrc: WHISPER_TINY,
-        modelType: "whisper",
-        modelConfig: {
-            audio_format: "f32le",
-            // Sampling strategy
-            strategy: "greedy",
-            n_threads: 4,
-            // Transcription options
-            language: "en",
-            translate: false,
-            no_timestamps: false,
-            single_segment: false,
-            print_timestamps: true,
-            token_timestamps: true,
-            // Quality settings
-            temperature: 0.0,
-            suppress_blank: true,
-            suppress_nst: true,
-            // Advanced tuning
-            entropy_thold: 2.4,
-            logprob_thold: -1.0,
-            // VAD configuration
-            vad_params: {
-                threshold: 0.35,
-                min_speech_duration_ms: 200,
-                min_silence_duration_ms: 150,
-                max_speech_duration_s: 30.0,
-                speech_pad_ms: 600,
-                samples_overlap: 0.3,
-            },
-            // Context parameters for GPU
-            contextParams: {
-                use_gpu: true,
-                flash_attn: true,
-                gpu_device: 0,
-            },
-        },
-        onProgress: (progress) => {
-            console.log(progress);
-        },
-    });
-    console.log(`✅ Whisper model loaded with ID: ${modelId}`);
-    // Perform transcription
-    console.log("🎧 Transcribing audio...");
-    const text = await transcribe({
-        modelId,
-        audioChunk: "examples/audio/sample-16khz.wav",
-        prompt: "This is a test recording with clear speech and proper punctuation.",
-    });
-    console.log("📝 Transcription result:");
-    console.log(text);
-    // Unload the model when done
-    console.log("🧹 Unloading Whisper model...");
-    await unloadModel({ modelId });
-    console.log("✅ Whisper model unloaded successfully");
-    process.exit(0);
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/translation/translation-bergamot-batch.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=translation-bergamot-batch.d.ts.map

package/dist/examples/translation/translation-bergamot-batch.js

@@ -1,49 +0,0 @@
-import { loadModel, translate, unloadModel, BERGAMOT_EN_FR } from "@qvac/sdk";
-try {
-    const modelId = await loadModel({
-        modelSrc: BERGAMOT_EN_FR,
-        modelType: "nmt",
-        modelConfig: {
-            engine: "Bergamot",
-            from: "en",
-            to: "fr",
-            beamsize: 1,
-            normalize: 1,
-            temperature: 0.2,
-            norepeatngramsize: 3,
-            lengthpenalty: 1.2,
-        },
-        onProgress: (progress) => {
-            console.log(progress);
-        },
-    });
-    console.log(`✅ Bergamot model loaded: ${modelId}`);
-    // Test with array of texts for batch processing
-    const texts = [
-        "Hello world",
-        "How are you today?",
-        "This is a test of batch translation",
-        "The weather is nice",
-    ];
-    console.log("\n📝 Translating batch of texts:");
-    texts.forEach((text, i) => console.log(`  ${i + 1}. ${text}`));
-    const result = translate({
-        modelId,
-        text: texts, // Pass array for batch processing
-        modelType: "nmt",
-        stream: false,
-    });
-    const translatedText = await result.text;
-    const translations = translatedText.split("\n");
-    console.log("\n✅ Translations:");
-    translations.forEach((translation, i) => {
-        if (i < texts.length) {
-            console.log(`  ${i + 1}. ${texts[i]} -> "${translation}"`);
-        }
-    });
-    await unloadModel({ modelId });
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/translation/translation-bergamot-pivot.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=translation-bergamot-pivot.d.ts.map

package/dist/examples/translation/translation-bergamot-pivot.js

@@ -1,73 +0,0 @@
-import { BERGAMOT_ES_EN, BERGAMOT_EN_IT, loadModel, translate, unloadModel } from "@qvac/sdk";
-/**
- * Example: Pivot Translation with Bergamot
- *
- * Demonstrates translating Spanish to Italian through English as a pivot language.
- * This requires two models:
- * 1. Spanish → English (primary model)
- * 2. English → Italian (pivot model)
- *
- * The API structure follows the standard Bergamot model pattern:
- * - modelSrc: Primary translation model
- * - modelConfig: Configuration with Bergamot-specific settings
- * - modelConfig.pivotModel: Configuration for the secondary model
- */
-// Spanish to Italian via English pivot example
-try {
-    // Load the primary model (Spanish → English) with pivot configuration
-    const modelId = await loadModel({
-        modelSrc: BERGAMOT_ES_EN, // Primary model: Spanish → English
-        modelType: "nmt",
-        modelConfig: {
-            engine: "Bergamot",
-            from: "es",
-            to: "it", // Final target language (SDK handles the pivot internally)
-            beamsize: 4,
-            normalize: 1,
-            temperature: 0.3,
-            topk: 100,
-            // Pivot model configuration (English → Italian)
-            pivotModel: {
-                modelSrc: BERGAMOT_EN_IT, // Source for English → Italian model
-                // Bergamot-specific generation parameters for pivot model
-                beamsize: 4,
-                temperature: 0.3,
-                topk: 100,
-                normalize: 1,
-                lengthpenalty: 1.2,
-            }
-        },
-        onProgress: (progress) => {
-            console.log(progress);
-        },
-    });
-    console.log(`✅ Pivot translation model loaded: ${modelId}`);
-    console.log("   Primary: Spanish → English");
-    console.log("   Pivot: English → Italian");
-    // Spanish text to translate
-    const spanishText = `Era una mañana soleada cuando María decidió visitar el mercado local.
-  Compró frutas frescas, verduras y flores para su casa.
-  El vendedor le recomendó las mejores manzanas de la temporada.`;
-    console.log("\n📝 Original Spanish text:");
-    console.log(spanishText);
-    // Translate Spanish → English → Italian
-    const result = translate({
-        modelId,
-        text: spanishText,
-        modelType: "nmt",
-        stream: false,
-    });
-    const italianText = await result.text;
-    console.log("\n🇮🇹 Translated to Italian (via English):");
-    console.log(italianText);
-    // Expected output (approximate):
-    // "Era una mattina di sole quando Maria decise di visitare il mercato locale.
-    //  Ha comprato frutta fresca, verdura e fiori per la sua casa.
-    //  Il venditore ha consigliato le migliori mele della stagione."
-    await unloadModel({ modelId });
-    console.log("\n✅ Model unloaded successfully");
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/translation/translation-bergamot.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=translation-bergamot.d.ts.map

package/dist/examples/translation/translation-bergamot.js

@@ -1,39 +0,0 @@
-import { loadModel, translate, unloadModel, BERGAMOT_EN_FR } from "@qvac/sdk";
-try {
-    // Bergamot models automatically derive vocabulary files from the model source.
-    // You can still override them explicitly if needed:
-    // - srcVocabSrc: source vocabulary file (optional)
-    // - dstVocabSrc: target vocabulary file (optional)
-    const modelId = await loadModel({
-        modelSrc: BERGAMOT_EN_FR,
-        modelType: "nmt",
-        modelConfig: {
-            engine: "Bergamot",
-            from: "en",
-            to: "fr",
-            beamsize: 1,
-            normalize: 1,
-            temperature: 0.2,
-            norepeatngramsize: 3,
-            lengthpenalty: 1.2,
-        },
-        onProgress: (progress) => {
-            console.log(progress);
-        },
-    });
-    console.log(`✅ Bergamot model loaded: ${modelId}`);
-    const text = "This is a test of the Bergamot translation model.";
-    const result = translate({
-        modelId,
-        text,
-        modelType: "nmt",
-        stream: false,
-    });
-    const translatedText = await result.text;
-    console.log(`Translated text EN -> FR: ${text} -> "${translatedText}"`);
-    await unloadModel({ modelId });
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/translation/translation-llm-afriquegemma.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=translation-llm-afriquegemma.d.ts.map

package/dist/examples/translation/translation-llm-afriquegemma.js

@@ -1,39 +0,0 @@
-import { translate, loadModel, unloadModel, AFRICAN_4B_TRANSLATION_Q4_K_M, } from "@qvac/sdk";
-try {
-    const modelId = await loadModel({
-        modelSrc: AFRICAN_4B_TRANSLATION_Q4_K_M,
-        modelType: "llm",
-        onProgress: (progress) => {
-            console.log(progress);
-        },
-        // IMPORTANT: these parameters are validated to be optimal
-        modelConfig: {
-            tools: true,
-            ctx_size: 2048,
-            top_k: 1,
-            top_p: 1,
-            temp: 0,
-            repeat_penalty: 1,
-            seed: 42,
-            predict: 256,
-            stop_sequences: ['\n']
-        }
-    });
-    // With explicit source language
-    const engText = "Hello, how are you today?";
-    const resultExplicit = translate({
-        modelId,
-        text: engText,
-        from: "en",
-        to: "swh_Latn",
-        modelType: "llm",
-        stream: false,
-    });
-    const translatedTextExplicit = await resultExplicit.text;
-    console.log(`Explicit source: ${engText} -> "${translatedTextExplicit}"`);
-    await unloadModel({ modelId, clearStorage: false });
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/tts/chatterbox.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=chatterbox.d.ts.map

package/dist/examples/tts/chatterbox.js

@@ -1,59 +0,0 @@
-import { loadModel, textToSpeech, unloadModel, TTS_TOKENIZER_EN_CHATTERBOX, TTS_SPEECH_ENCODER_EN_CHATTERBOX_FP32, TTS_EMBED_TOKENS_EN_CHATTERBOX_FP32, TTS_CONDITIONAL_DECODER_EN_CHATTERBOX_FP32, TTS_LANGUAGE_MODEL_EN_CHATTERBOX_FP32, } from "@qvac/sdk";
-import { createWav, playAudio, int16ArrayToBuffer, createWavHeader, } from "./utils.js";
-// Chatterbox TTS: voice cloning with reference audio.
-// Uses registry model constants - downloads automatically from QVAC Registry.
-// Only reference audio WAV needs to be provided by the user.
-// Usage: node chatterbox-filesystem.js <referenceAudioSrc>
-const [referenceAudioSrc] = process.argv.slice(2);
-if (!referenceAudioSrc) {
-    console.error("Usage: node chatterbox-filesystem.js <referenceAudioSrc>");
-    process.exit(1);
-}
-const CHATTERBOX_SAMPLE_RATE = 24000;
-try {
-    const modelId = await loadModel({
-        modelSrc: TTS_TOKENIZER_EN_CHATTERBOX.src,
-        modelType: "tts",
-        modelConfig: {
-            ttsEngine: "chatterbox",
-            language: "en",
-            ttsTokenizerSrc: TTS_TOKENIZER_EN_CHATTERBOX.src,
-            ttsSpeechEncoderSrc: TTS_SPEECH_ENCODER_EN_CHATTERBOX_FP32.src,
-            ttsEmbedTokensSrc: TTS_EMBED_TOKENS_EN_CHATTERBOX_FP32.src,
-            ttsConditionalDecoderSrc: TTS_CONDITIONAL_DECODER_EN_CHATTERBOX_FP32.src,
-            ttsLanguageModelSrc: TTS_LANGUAGE_MODEL_EN_CHATTERBOX_FP32.src,
-            referenceAudioSrc,
-        },
-        onProgress: (progress) => {
-            console.log(progress);
-        },
-    });
-    console.log(`Model loaded: ${modelId}`);
-    console.log("🎵 Testing Text-to-Speech...");
-    const result = textToSpeech({
-        modelId,
-        text: `QVAC SDK is the canonical entry point to QVAC. Written in TypeScript, it provides all QVAC capabilities through a unified interface while also abstracting away the complexity of running your application in a JS environment other than Bare. Supported JS environments include Bare, Node.js, Expo and Bun.`,
-        inputType: "text",
-        stream: false,
-    });
-    const audioBuffer = await result.buffer;
-    console.log(`TTS complete. Total bytes: ${audioBuffer.length}`);
-    console.log("💾 Saving audio to file...");
-    createWav(audioBuffer, CHATTERBOX_SAMPLE_RATE, "tts-output.wav");
-    console.log("✅ Audio saved to tts-output.wav");
-    console.log("🔊 Playing audio...");
-    const audioData = int16ArrayToBuffer(audioBuffer);
-    const wavBuffer = Buffer.concat([
-        createWavHeader(audioData.length, CHATTERBOX_SAMPLE_RATE),
-        audioData,
-    ]);
-    playAudio(wavBuffer);
-    console.log("✅ Audio playback complete");
-    await unloadModel({ modelId });
-    console.log("Model unloaded");
-    process.exit(0);
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/tts/supertonic.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=supertonic.d.ts.map

package/dist/examples/tts/supertonic.js

@@ -1,51 +0,0 @@
-import { loadModel, textToSpeech, unloadModel, TTS_TOKENIZER_SUPERTONIC, TTS_TEXT_ENCODER_SUPERTONIC_FP32, TTS_LATENT_DENOISER_SUPERTONIC_FP32, TTS_VOICE_DECODER_SUPERTONIC_FP32, TTS_VOICE_STYLE_SUPERTONIC, } from "@qvac/sdk";
-import { createWav, playAudio, int16ArrayToBuffer, createWavHeader, } from "./utils.js";
-// Supertonic TTS: general-purpose, no voice cloning.
-// Uses registry model constants - downloads automatically from QVAC Registry.
-const SUPERTONIC_SAMPLE_RATE = 44100;
-try {
-    const modelId = await loadModel({
-        modelSrc: TTS_TOKENIZER_SUPERTONIC.src,
-        modelType: "tts",
-        modelConfig: {
-            ttsEngine: "supertonic",
-            language: "en",
-            ttsTokenizerSrc: TTS_TOKENIZER_SUPERTONIC.src,
-            ttsTextEncoderSrc: TTS_TEXT_ENCODER_SUPERTONIC_FP32.src,
-            ttsLatentDenoiserSrc: TTS_LATENT_DENOISER_SUPERTONIC_FP32.src,
-            ttsVoiceDecoderSrc: TTS_VOICE_DECODER_SUPERTONIC_FP32.src,
-            ttsVoiceSrc: TTS_VOICE_STYLE_SUPERTONIC.src,
-        },
-        onProgress: (progress) => {
-            console.log(progress);
-        },
-    });
-    console.log(`Model loaded: ${modelId}`);
-    console.log("🎵 Testing Text-to-Speech...");
-    const result = textToSpeech({
-        modelId,
-        text: `QVAC SDK is the canonical entry point to QVAC. Written in TypeScript, it provides all QVAC capabilities through a unified interface while also abstracting away the complexity of running your application in a JS environment other than Bare. Supported JS environments include Bare, Node.js, Expo and Bun.`,
-        inputType: "text",
-        stream: false,
-    });
-    const audioBuffer = await result.buffer;
-    console.log(`TTS complete. Total samples: ${audioBuffer.length}`);
-    console.log("💾 Saving audio to file...");
-    createWav(audioBuffer, SUPERTONIC_SAMPLE_RATE, "supertonic-output.wav");
-    console.log("✅ Audio saved to supertonic-output.wav");
-    console.log("🔊 Playing audio...");
-    const audioData = int16ArrayToBuffer(audioBuffer);
-    const wavBuffer = Buffer.concat([
-        createWavHeader(audioData.length, SUPERTONIC_SAMPLE_RATE),
-        audioData,
-    ]);
-    playAudio(wavBuffer);
-    console.log("✅ Audio playback complete");
-    await unloadModel({ modelId });
-    console.log("Model unloaded");
-    process.exit(0);
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/tts/utils.d.ts

@@ -1,17 +0,0 @@
-/**
- * Create WAV header for 16-bit PCM audio
- */
-export declare function createWavHeader(dataLength: number, sampleRate: number): Buffer;
-/**
- * Convert Int16Array to Buffer
- */
-export declare function int16ArrayToBuffer(samples: number[]): Buffer;
-/**
- * Create and save WAV file
- */
-export declare function createWav(audioBuffer: number[], sampleRate: number, filename: string): void;
-/**
- * Play audio using system audio players
- */
-export declare function playAudio(audioBuffer: Buffer): void;
-//# sourceMappingURL=utils.d.ts.map