@qvac/sdk 0.10.2 → 0.12.0

package/dist/examples/transcription/parakeet-microphone-stream.js

@@ -0,0 +1,79 @@
+/**
+ * Microphone → Parakeet duplex streaming (`transcribeStream`).
+ *
+ * Usage:
+ *   bun run examples/transcription/parakeet-microphone-stream.ts
+ *
+ * Streams microphone audio through `transcribeStream` with
+ * `parakeetStreamingConfig`. Uses the EOU checkpoint so you may see
+ * `{ type: "endOfTurn", source: "parakeet" }` events; CTC/TDT models
+ * emit transcript text only. Parakeet does not yield standalone VAD events.
+ *
+ * Requirements: FFmpeg installed, microphone access.
+ */
+import { loadModel, unloadModel, transcribeStream, PARAKEET_EOU_120M_V1_Q8_0, } from "@qvac/sdk";
+import { spawnSync } from "child_process";
+import { startMicrophone } from "../audio/mic-input";
+const SAMPLE_RATE = 16000;
+try {
+    const r = spawnSync("ffmpeg", ["-version"], { stdio: "ignore" });
+    if (r.error || r.status !== 0)
+        throw new Error("FFmpeg not found");
+}
+catch {
+    console.error("Error: FFmpeg is required. Install it and try again.");
+    process.exit(1);
+}
+let modelId = null;
+let ffmpeg = null;
+async function cleanup() {
+    console.log("\n\nStopping...");
+    ffmpeg?.kill();
+    if (modelId)
+        await unloadModel({ modelId });
+    console.log("Done.");
+}
+process.on("SIGINT", () => {
+    void cleanup().finally(() => process.exit(0));
+});
+process.on("SIGTERM", () => {
+    void cleanup().finally(() => process.exit(0));
+});
+try {
+    console.log("Loading Parakeet (EOU) streaming model...");
+    modelId = await loadModel({
+        modelSrc: PARAKEET_EOU_120M_V1_Q8_0,
+        modelType: "parakeet",
+        onProgress: (p) => console.log(`Download: ${p.percentage.toFixed(1)}%`),
+    });
+    console.log("Model loaded.\n");
+    ffmpeg = startMicrophone({ sampleRate: SAMPLE_RATE, format: "s16le" });
+    const session = await transcribeStream({
+        modelId,
+        parakeetStreamingConfig: {
+            chunkMs: 1000,
+            emitPartials: true,
+        },
+    });
+    ffmpeg.stdout.on("data", (chunk) => session.write(chunk));
+    console.log("Listening... speak and pause to see transcripts. End-of-turn boundaries fire when the EOU model emits an <EOU> token.\n");
+    for await (const event of session) {
+        switch (event.type) {
+            case "text":
+                if (event.text.trim()) {
+                    process.stdout.write(`${event.text}`);
+                }
+                break;
+            case "endOfTurn":
+                console.log("\n[endOfTurn] turn boundary detected\n");
+                break;
+        }
+    }
+    await cleanup();
+    process.exit(0);
+}
+catch (error) {
+    console.error("Error:", error);
+    await cleanup();
+    process.exit(1);
+}

package/dist/examples/transcription/parakeet-sortformer-streaming.d.ts

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

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

@@ -0,0 +1,121 @@
+/**
+ * Sortformer v2.1 streaming diarization via duplex `transcribeStream` + AOSC.
+ *
+ * Usage:
+ *   bun run examples/transcription/parakeet-sortformer-streaming.ts <wav-file> [sortformer-gguf]
+ *
+ * Streams 16 kHz mono s16le audio in real-time-paced chunks (required for parakeet
+ * duplex streaming). Loads v2.1 with AOSC knobs in `modelConfig`. Omit the model
+ * argument to use `PARAKEET_SORTFORMER_4SPK_V2_1_Q8_0`.
+ *
+ * For offline batch diarization (Sortformer + TDT), see `parakeet-sortformer.ts`.
+ */
+import { loadModel, unloadModel, transcribeStream, PARAKEET_SORTFORMER_4SPK_V2_1_Q8_0, } from "@qvac/sdk";
+import { spawn } from "child_process";
+const SAMPLE_RATE = 16000;
+const BYTES_PER_S16_SAMPLE = 2;
+const STREAM_CHUNK_MS = 2000;
+/** NeMo-port AOSC defaults for v2.1 Sortformer (`parakeet.model_variant` in GGUF). */
+const SORTFORMER_V21_AOSC_LOAD_CONFIG = {
+    streaming: true,
+    streamingChunkMs: 2000,
+    streamingChunkRightContextMs: 560,
+    streamingSpkCacheEnable: true,
+    streamingSpkCacheLen: 188,
+    streamingFifoLen: 188,
+    streamingChunkLeftContextMs: 80,
+    streamingSpkCacheUpdatePeriod: 144,
+};
+const args = process.argv.slice(2);
+if (!args[0]) {
+    console.error("Usage: bun run examples/transcription/parakeet-sortformer-streaming.ts <wav-file-path> [sortformer-gguf]");
+    console.error("\nDefaults to the v2.1 q8_0 registry model (PARAKEET_SORTFORMER_4SPK_V2_1_Q8_0).");
+    process.exit(1);
+}
+const audioFilePath = args[0];
+const sortformerOverride = args[1];
+const chunkBytes = Math.floor((STREAM_CHUNK_MS / 1000) * SAMPLE_RATE) * BYTES_PER_S16_SAMPLE;
+let modelId = null;
+async function cleanup() {
+    if (modelId) {
+        await unloadModel({ modelId });
+    }
+}
+function readS16leFromWav(wavPath) {
+    return new Promise((resolve, reject) => {
+        const chunks = [];
+        const proc = spawn("ffmpeg", [
+            "-i",
+            wavPath,
+            "-ar",
+            String(SAMPLE_RATE),
+            "-ac",
+            "1",
+            "-f",
+            "s16le",
+            "pipe:1",
+        ], { stdio: ["ignore", "pipe", "ignore"] });
+        proc.stdout.on("data", (buf) => chunks.push(buf));
+        proc.on("error", reject);
+        proc.on("close", (code) => {
+            if (code !== 0) {
+                reject(new Error(`ffmpeg exited with code ${code}`));
+                return;
+            }
+            const merged = Buffer.concat(chunks);
+            resolve(new Uint8Array(merged.buffer, merged.byteOffset, merged.byteLength));
+        });
+    });
+}
+const loadOptions = {
+    modelType: "parakeet-transcription",
+    modelConfig: { ...SORTFORMER_V21_AOSC_LOAD_CONFIG },
+    onProgress: (p) => console.log(`Download: ${p.percentage.toFixed(1)}%`),
+    ...(sortformerOverride
+        ? { modelSrc: sortformerOverride }
+        : { modelSrc: PARAKEET_SORTFORMER_4SPK_V2_1_Q8_0 }),
+};
+try {
+    console.log("Loading Sortformer v2.1 with streaming + AOSC (load-time config)...");
+    modelId = await loadModel(loadOptions);
+    console.log(`Model loaded: ${modelId}\n`);
+    const session = await transcribeStream({
+        modelId,
+        parakeetStreamingConfig: { chunkMs: STREAM_CHUNK_MS },
+    });
+    console.log(`Streaming ${audioFilePath} in ${STREAM_CHUNK_MS}ms chunks (wall-clock paced)...\n`);
+    const pcm = await readS16leFromWav(audioFilePath);
+    const trailingSilenceMs = 1500;
+    const trailingBytes = new Uint8Array(Math.floor((trailingSilenceMs / 1000) * SAMPLE_RATE) * BYTES_PER_S16_SAMPLE);
+    for (let offset = 0; offset < pcm.length; offset += chunkBytes) {
+        const end = Math.min(offset + chunkBytes, pcm.length);
+        session.write(pcm.subarray(offset, end));
+        if (end < pcm.length) {
+            await new Promise((resolve) => setTimeout(resolve, STREAM_CHUNK_MS));
+        }
+    }
+    for (let offset = 0; offset < trailingBytes.length; offset += chunkBytes) {
+        const end = Math.min(offset + chunkBytes, trailingBytes.length);
+        session.write(trailingBytes.subarray(offset, end));
+        if (end < trailingBytes.length) {
+            await new Promise((resolve) => setTimeout(resolve, STREAM_CHUNK_MS));
+        }
+    }
+    session.end();
+    const lines = [];
+    for await (const event of session) {
+        if (event.type === "text" && event.text.trim()) {
+            lines.push(event.text.trim());
+            console.log(event.text.trim());
+        }
+    }
+    console.log("\n=== Streaming diarization transcript ===");
+    console.log(lines.join("\n") || "(no speaker lines emitted)");
+    await cleanup();
+    process.exit(0);
+}
+catch (error) {
+    console.error("❌ Error:", error);
+    await cleanup();
+    process.exit(1);
+}

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

@@ -1,75 +1,78 @@
 /**
- * Parakeet Sortformer diarization + TDT transcription example.
+ * Parakeet Sortformer diarization + TDT transcription pipeline.
  *
  * Usage:
- *   bun examples/transcription/parakeet-sortformer.ts [sortformer-src] [path-to-audio]
+ *   bun run examples/transcription/parakeet-sortformer.ts [sortformer-gguf] [wav-file]
  *
- * This example requires a test audio file (default: examples/audio/diarization-sample-16k.wav).
- * Sample audio files are available in the QVAC source repository, but not included in the published npm package.
- * Pass a custom audio path as the second argument, or download the default audio into examples/audio/:
+ * Two-step flow: Sortformer v2.1 diarizes the audio, then TDT transcribes each
+ * speaker segment. Defaults to registry GGUFs and
+ * `examples/audio/diarization-sample-16k.wav`. For live streaming + AOSC, see
+ * `parakeet-sortformer-streaming.ts`.
+ *
+ * Sample audio is in the QVAC source repo but not the published npm package.
+ * Download the default file into `examples/audio/`:
  *   https://github.com/tetherto/qvac/blob/main/packages/sdk/examples/audio/diarization-sample-16k.wav
  */
-import { loadModel, unloadModel, transcribe, PARAKEET_TDT_ENCODER_FP32, PARAKEET_TDT_DECODER_FP32, PARAKEET_TDT_VOCAB, PARAKEET_TDT_PREPROCESSOR_FP32, PARAKEET_SORTFORMER_FP32, } from "@qvac/sdk";
+import { loadModel, unloadModel, transcribe, PARAKEET_TDT_0_6B_V3_Q8_0, PARAKEET_SORTFORMER_4SPK_V2_1_Q8_0, } 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 sortformerSrc = args[0] ?? PARAKEET_SORTFORMER_4SPK_V2_1_Q8_0;
 const defaultAudioPath = join(__dirname, "..", "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,
-        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;
+try {
+    // ── Step 1: Diarize with Sortformer ──
+    const sfModelId = await loadModel({
+        modelSrc: sortformerSrc,
+        modelType: "parakeet",
+    });
+    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_0_6B_V3_Q8_0,
+        modelType: "parakeet",
+    });
+    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`);
     }
-    const text = await transcribe({ modelId: tdtModelId, audioChunk: slicePath });
-    results.push({ ...seg, text: text.trim() || "[No speech detected]" });
+    console.log("=".repeat(60));
+    console.log("\nDone!");
 }
-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`);
+catch (error) {
+    console.error("❌ Error:", error);
+    process.exit(1);
 }
-console.log("=".repeat(60));
-console.log("\nDone!");
 // ── Helpers ──
 function parseDiarization(text) {
     const segs = [];

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

@@ -1,28 +1,31 @@
-import { loadModel, unloadModel, transcribe, PARAKEET_TDT_ENCODER_FP32, PARAKEET_TDT_DECODER_FP32, PARAKEET_TDT_VOCAB, PARAKEET_TDT_PREPROCESSOR_FP32, } from "@qvac/sdk";
+/**
+ * Parakeet TDT transcription from a WAV file.
+ *
+ * Usage:
+ *   bun run examples/transcription/parakeet-tdt-filesystem.ts <wav-file> [parakeet-tdt-gguf]
+ *
+ * Loads a single GGUF checkpoint (`PARAKEET_TDT_0_6B_V3_Q8_0` by default) and
+ * transcribes the file with the batch `transcribe` API. Omit the model
+ * argument to use the registry constant.
+ *
+ * Audio should be 16 kHz mono PCM in a WAV container.
+ */
+import { loadModel, unloadModel, transcribe, PARAKEET_TDT_0_6B_V3_Q8_0, } 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] [decoder-onnx] [vocab-txt] [preprocessor-onnx]");
-    console.error("\nIf model paths are omitted, defaults to registry models.");
+        "[parakeet-tdt-gguf]");
+    console.error("\nIf the model path is omitted, defaults to the registry model.");
     process.exit(1);
 }
 const audioFilePath = args[0];
-const parakeetEncoderSrc = args[1] ?? PARAKEET_TDT_ENCODER_FP32;
-const parakeetDecoderSrc = args[2] ?? PARAKEET_TDT_DECODER_FP32;
-const parakeetVocabSrc = args[3] ?? PARAKEET_TDT_VOCAB;
-const parakeetPreprocessorSrc = args[4] ?? PARAKEET_TDT_PREPROCESSOR_FP32;
+const parakeetModelSrc = args[1] ?? PARAKEET_TDT_0_6B_V3_Q8_0;
 try {
     console.log("Starting Parakeet transcription example...");
     console.log("Loading Parakeet model...");
     const modelId = await loadModel({
-        modelSrc: parakeetEncoderSrc,
+        modelSrc: parakeetModelSrc,
         modelType: "parakeet",
-        modelConfig: {
-            parakeetEncoderSrc,
-            parakeetDecoderSrc,
-            parakeetVocabSrc,
-            parakeetPreprocessorSrc,
-        },
         onProgress: (progress) => {
             console.log(`Download progress: ${progress.percentage.toFixed(1)}%`);
         },
@@ -37,6 +40,6 @@ try {
     console.log("Parakeet model unloaded successfully");
 }
 catch (error) {
-    console.error("Error:", error);
+    console.error("❌ Error:", error);
     process.exit(1);
 }

package/dist/examples/transcription/whispercpp-microphone-conversation.d.ts

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

package/dist/examples/transcription/whispercpp-microphone-conversation.js

@@ -0,0 +1,107 @@
+/**
+ * Microphone → Whisper streaming transcription with conversation events
+ * (VAD state updates + end-of-turn detection).
+ *
+ * Demonstrates the opt-in conversation API:
+ *   transcribeStream({ modelId, emitVadEvents: true, endOfTurnSilenceMs: N })
+ *
+ * The session yields a discriminated union of events:
+ *   - { type: "text", text }                      transcript chunks
+ *   - { type: "vad", speaking, probability }      VAD state updates
+ *   - { type: "endOfTurn", silenceDurationMs }    silence boundary
+ *
+ * Speak into your mic; transcripts appear as you pause, VAD ticks while
+ * you speak, and an end-of-turn event fires after 800ms of silence.
+ * Press Ctrl+C to quit.
+ *
+ * Requirements: FFmpeg installed, microphone access.
+ */
+import { loadModel, unloadModel, transcribeStream, WHISPER_TINY, VAD_SILERO_5_1_2, } from "@qvac/sdk";
+import { spawnSync } from "child_process";
+import { startMicrophone } from "../audio/mic-input";
+const SAMPLE_RATE = 16000;
+try {
+    const r = spawnSync("ffmpeg", ["-version"], { stdio: "ignore" });
+    if (r.error || r.status !== 0)
+        throw new Error("FFmpeg not found");
+}
+catch {
+    console.error("❌ Error: FFmpeg is required. Install it and try again.");
+    process.exit(1);
+}
+let modelId = null;
+let ffmpeg = null;
+async function cleanup() {
+    console.log("\n\nStopping...");
+    ffmpeg?.kill();
+    if (modelId)
+        await unloadModel({ modelId });
+    console.log("Done.");
+}
+process.on("SIGINT", () => {
+    void cleanup().finally(() => process.exit(0));
+});
+process.on("SIGTERM", () => {
+    void cleanup().finally(() => process.exit(0));
+});
+try {
+    console.log("Loading model (whisper-tiny + Silero VAD)...");
+    modelId = await loadModel({
+        modelSrc: WHISPER_TINY,
+        modelType: "whisper",
+        modelConfig: {
+            vadModelSrc: VAD_SILERO_5_1_2,
+            audio_format: "f32le",
+            strategy: "greedy",
+            n_threads: 4,
+            language: "en",
+            no_timestamps: true,
+            suppress_blank: true,
+            suppress_nst: true,
+            temperature: 0.0,
+            vad_params: {
+                threshold: 0.6,
+                min_speech_duration_ms: 250,
+                min_silence_duration_ms: 300,
+                max_speech_duration_s: 15.0,
+                speech_pad_ms: 100,
+            },
+        },
+    });
+    console.log("Model loaded.\n");
+    ffmpeg = startMicrophone({ sampleRate: SAMPLE_RATE, format: "f32le" });
+    const session = await transcribeStream({
+        modelId,
+        emitVadEvents: true,
+        endOfTurnSilenceMs: 800,
+    });
+    ffmpeg.stdout.on("data", (chunk) => session.write(chunk));
+    console.log("Listening... speak and pause to see transcripts, VAD events, and end-of-turn signals.\n");
+    let lastSpeaking = false;
+    for await (const event of session) {
+        switch (event.type) {
+            case "text":
+                console.log(`> ${event.text.trim()}`);
+                break;
+            case "vad":
+                if (event.speaking !== lastSpeaking) {
+                    console.log(`[vad] speaking=${event.speaking} probability=${event.probability.toFixed(2)}`);
+                    lastSpeaking = event.speaking;
+                }
+                break;
+            case "endOfTurn":
+                if (event.source === "whisper") {
+                    console.log(`[endOfTurn] silence ${event.silenceDurationMs}ms — turn complete\n`);
+                }
+                else {
+                    console.log(`[endOfTurn] turn complete (token-driven EOU)\n`);
+                }
+                break;
+        }
+    }
+}
+catch (error) {
+    console.error("❌ Error:", error);
+    await cleanup();
+    process.exit(1);
+}

package/dist/examples/tts/chatterbox.js

@@ -1,28 +1,19 @@
-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 { loadModel, textToSpeech, unloadModel, TTS_T3_TURBO_EN_CHATTERBOX_Q8_0, TTS_S3GEN_EN_CHATTERBOX, } 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>
+// Chatterbox TTS (GGML): voice cloning with optional reference audio.
+// Uses registry model constants — downloads automatically from QVAC Registry.
+// Usage: node chatterbox.ts [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,
+        modelSrc: TTS_T3_TURBO_EN_CHATTERBOX_Q8_0.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,
+            s3genModelSrc: TTS_S3GEN_EN_CHATTERBOX.src,
+            ...(referenceAudioSrc ? { referenceAudioSrc } : {}),
         },
         onProgress: (progress) => {
             console.log(progress);

package/dist/examples/tts/llm-to-tts-streaming.js

@@ -12,7 +12,7 @@
  * Usage:
  *   bun run examples/tts/llm-to-tts-streaming.ts
  */
-import { completion, loadModel, textToSpeechStream, unloadModel, LLAMA_3_2_1B_INST_Q4_0, TTS_SUPERTONIC2_OFFICIAL_TEXT_ENCODER_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_DURATION_PREDICTOR_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_VECTOR_ESTIMATOR_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_VOCODER_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_UNICODE_INDEXER_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_TTS_CONFIG_SUPERTONE, TTS_SUPERTONIC2_OFFICIAL_VOICE_STYLE_SUPERTONE, } from "@qvac/sdk";
+import { completion, loadModel, textToSpeechStream, unloadModel, LLAMA_3_2_1B_INST_Q4_0, TTS_EN_SUPERTONIC_Q8_0, } from "@qvac/sdk";
 import { createWav, playPcmInt16Chunk } from "./utils.js";
 const SUPERTONIC_SAMPLE_RATE = 44100;
 /**
@@ -69,21 +69,14 @@ try {
     console.log(`LLM ready: ${llmModelId}`);
     console.log("Loading Supertonic TTS (registry)…");
     const ttsModelId = await loadModel({
-        modelSrc: TTS_SUPERTONIC2_OFFICIAL_TEXT_ENCODER_SUPERTONE_FP32.src,
+        modelSrc: TTS_EN_SUPERTONIC_Q8_0.src,
         modelType: "tts",
         modelConfig: {
             ttsEngine: "supertonic",
             language: "en",
+            voice: "F1",
             ttsSpeed: 1.05,
             ttsNumInferenceSteps: 10,
-            ttsSupertonicMultilingual: true,
-            ttsTextEncoderSrc: TTS_SUPERTONIC2_OFFICIAL_TEXT_ENCODER_SUPERTONE_FP32.src,
-            ttsDurationPredictorSrc: TTS_SUPERTONIC2_OFFICIAL_DURATION_PREDICTOR_SUPERTONE_FP32.src,
-            ttsVectorEstimatorSrc: TTS_SUPERTONIC2_OFFICIAL_VECTOR_ESTIMATOR_SUPERTONE_FP32.src,
-            ttsVocoderSrc: TTS_SUPERTONIC2_OFFICIAL_VOCODER_SUPERTONE_FP32.src,
-            ttsUnicodeIndexerSrc: TTS_SUPERTONIC2_OFFICIAL_UNICODE_INDEXER_SUPERTONE_FP32.src,
-            ttsTtsConfigSrc: TTS_SUPERTONIC2_OFFICIAL_TTS_CONFIG_SUPERTONE.src,
-            ttsVoiceStyleSrc: TTS_SUPERTONIC2_OFFICIAL_VOICE_STYLE_SUPERTONE.src,
         },
         onProgress: (progress) => console.log(`TTS load: ${progress.percentage.toFixed(1)}%`),
     });

package/dist/examples/tts/supertonic-multilingual.js

@@ -1,25 +1,17 @@
-import { loadModel, textToSpeech, unloadModel, TTS_SUPERTONIC2_OFFICIAL_TEXT_ENCODER_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_DURATION_PREDICTOR_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_VECTOR_ESTIMATOR_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_VOCODER_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_TTS_CONFIG_SUPERTONE, TTS_SUPERTONIC2_OFFICIAL_VOICE_STYLE_SUPERTONE, TTS_SUPERTONIC2_OFFICIAL_UNICODE_INDEXER_SUPERTONE_FP32, } from "@qvac/sdk";
+import { loadModel, textToSpeech, unloadModel, TTS_MULTILINGUAL_SUPERTONIC2_Q8_0, } 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.
+// Supertonic 2 TTS (GGML): multilingual synthesis (en/ko/es/pt/fr).
 const SUPERTONIC_SAMPLE_RATE = 44100;
 try {
     const modelId = await loadModel({
-        modelSrc: TTS_SUPERTONIC2_OFFICIAL_TEXT_ENCODER_SUPERTONE_FP32.src,
+        modelSrc: TTS_MULTILINGUAL_SUPERTONIC2_Q8_0.src,
         modelType: "tts",
         modelConfig: {
             ttsEngine: "supertonic",
             language: "es",
+            voice: "F1",
             ttsSpeed: 1.05,
             ttsNumInferenceSteps: 5,
-            ttsSupertonicMultilingual: true, //false for English quality.
-            ttsTextEncoderSrc: TTS_SUPERTONIC2_OFFICIAL_TEXT_ENCODER_SUPERTONE_FP32.src,
-            ttsDurationPredictorSrc: TTS_SUPERTONIC2_OFFICIAL_DURATION_PREDICTOR_SUPERTONE_FP32.src,
-            ttsVectorEstimatorSrc: TTS_SUPERTONIC2_OFFICIAL_VECTOR_ESTIMATOR_SUPERTONE_FP32.src,
-            ttsVocoderSrc: TTS_SUPERTONIC2_OFFICIAL_VOCODER_SUPERTONE_FP32.src,
-            ttsUnicodeIndexerSrc: TTS_SUPERTONIC2_OFFICIAL_UNICODE_INDEXER_SUPERTONE_FP32.src,
-            ttsTtsConfigSrc: TTS_SUPERTONIC2_OFFICIAL_TTS_CONFIG_SUPERTONE.src,
-            ttsVoiceStyleSrc: TTS_SUPERTONIC2_OFFICIAL_VOICE_STYLE_SUPERTONE.src,
         },
         onProgress: (progress) => {
             console.log(progress);

package/dist/examples/tts/supertonic.js

@@ -1,25 +1,18 @@
-import { loadModel, textToSpeech, unloadModel, TTS_SUPERTONIC2_OFFICIAL_TEXT_ENCODER_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_DURATION_PREDICTOR_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_VECTOR_ESTIMATOR_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_VOCODER_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_UNICODE_INDEXER_SUPERTONE_FP32, TTS_SUPERTONIC2_OFFICIAL_TTS_CONFIG_SUPERTONE, TTS_SUPERTONIC2_OFFICIAL_VOICE_STYLE_SUPERTONE, } from "@qvac/sdk";
+import { loadModel, textToSpeech, unloadModel, TTS_EN_SUPERTONIC_Q8_0, } 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.
+// Supertonic TTS (GGML): fast English synthesis with baked-in voices.
+// Uses registry model constants — downloads automatically from QVAC Registry.
 const SUPERTONIC_SAMPLE_RATE = 44100;
 try {
     const modelId = await loadModel({
-        modelSrc: TTS_SUPERTONIC2_OFFICIAL_TEXT_ENCODER_SUPERTONE_FP32.src,
+        modelSrc: TTS_EN_SUPERTONIC_Q8_0.src,
         modelType: "tts",
         modelConfig: {
             ttsEngine: "supertonic",
             language: "en",
+            voice: "F1",
             ttsSpeed: 1.05,
             ttsNumInferenceSteps: 5,
-            ttsSupertonicMultilingual: false, //false for English quality.
-            ttsTextEncoderSrc: TTS_SUPERTONIC2_OFFICIAL_TEXT_ENCODER_SUPERTONE_FP32.src,
-            ttsDurationPredictorSrc: TTS_SUPERTONIC2_OFFICIAL_DURATION_PREDICTOR_SUPERTONE_FP32.src,
-            ttsVectorEstimatorSrc: TTS_SUPERTONIC2_OFFICIAL_VECTOR_ESTIMATOR_SUPERTONE_FP32.src,
-            ttsVocoderSrc: TTS_SUPERTONIC2_OFFICIAL_VOCODER_SUPERTONE_FP32.src,
-            ttsUnicodeIndexerSrc: TTS_SUPERTONIC2_OFFICIAL_UNICODE_INDEXER_SUPERTONE_FP32.src,
-            ttsTtsConfigSrc: TTS_SUPERTONIC2_OFFICIAL_TTS_CONFIG_SUPERTONE.src,
-            ttsVoiceStyleSrc: TTS_SUPERTONIC2_OFFICIAL_VOICE_STYLE_SUPERTONE.src,
         },
         onProgress: (progress) => {
             console.log(progress);

package/dist/examples/vla-smolvla.d.ts

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