feat: share voices across 1.7B and 0.6B via per-model embeddings (v6.14.0)

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

README.md

@@ -378,6 +378,14 @@ The first request after container startup can be slower because CUDA graph captu
 
 ## Changelog
 
+### v6.14.0 — 2026-10-11
+
+- **Feature:** `EMBED_TAG` environment variable (e.g. `1.7b`, `0.6b`). Speaker embeddings are stored beside the reference audio as `<name>.<tag>.pt`, so a 1.7B VoiceClone and a 0.6B Streaming backend can share one `voices.json` and one voice folder (mount `/voices` read-write). Existing `config/speakers/*.pt` files are adopted once for the `1.7b` tag; embeddings older than their WAV/TXT are regenerated.
+- **Feature:** `/voices` and `/v1/voices` discovery endpoints on all backends.
+- **Config:** new `docker/docker-compose.portainer-0.6b.yml` — 1.7B VoiceClone on :8020 plus 0.6B-Base Streaming on :8023 (`--max-seq-len 2048`). The 0.6B model needs its own embeddings (1024-dim); never share `.pt` files between model sizes.
+- **Image:** unchanged (`:v6.13.1`); the changes live in `/config` (bind mount), no rebuild needed.
+- **Rollback:** redeploy the previous compose file (`:v6.13.1` images); `EMBED_TAG` unset keeps the old `/config/speakers` behaviour.
+
 ### v6.13.1 — 2026-10-04
 
 - **Fix:** Streaming must use the same model size as the one voices.json was built for (1.7B-Base), otherwise requests fail with a 1024 vs 2048 tensor size mismatch. Streaming compose examples now default to the 1.7B-Base model.

config/run_customvoice_server.py

@@ -321,6 +321,12 @@ async def list_audio_models():
     return _models_response
 
 
+@app.get("/voices")
+@app.get("/v1/voices")
+async def list_voices():
+    return _models_response
+
+
 @app.get("/speakers")
 async def get_speakers():
     return list(voices.keys())

config/run_server.py

@@ -32,6 +32,46 @@ import openai_server
 logger = logging.getLogger(__name__)
 
 
+# Speaker embeddings (.pt) are model-size specific (1.7B=2048-dim, 0.6B=1024-dim).
+# With EMBED_TAG set (e.g. "1.7b"/"0.6b") every voice's embedding lives next to its
+# reference audio as <name>.<tag>.pt, so several model sizes can share one voices.json.
+_EMBED_TAG = os.environ.get("EMBED_TAG", "").strip()
+
+
+def _retarget_embeddings(voice_cfg: dict) -> dict:
+    """Point voice_cfg at the per-model .pt beside the reference audio (idempotent)."""
+    ref_audio = voice_cfg.get("ref_audio")
+    if not _EMBED_TAG or not ref_audio or voice_cfg.get("_emb_tag") == _EMBED_TAG:
+        return voice_cfg
+    stem = os.path.splitext(ref_audio)[0]
+    pt = f"{stem}.{_EMBED_TAG}.pt"
+    legacy = voice_cfg.get("speaker_embeddings") or ""
+    try:
+        # ponytail: legacy /config/speakers/*.pt are 1.7B embeddings; adopt them once for the 1.7b tag only.
+        if _EMBED_TAG.lower() == "1.7b" and not os.path.exists(pt) and os.path.isfile(legacy):
+            import shutil
+            shutil.copy2(legacy, pt)
+        if os.path.exists(pt):
+            sources = [ref_audio, stem + ".txt", stem + ".reference.txt"]
+            newest = max(os.path.getmtime(f) for f in sources if os.path.exists(f))
+            if newest > os.path.getmtime(pt) + 1:  # reference changed -> embedding stale
+                os.remove(pt)
+    except OSError as exc:
+        logger.warning("Embedding retarget problem for %s: %s", pt, exc)
+    voice_cfg["speaker_embeddings"] = pt
+    voice_cfg["_emb_tag"] = _EMBED_TAG
+    return voice_cfg
+
+
+if _EMBED_TAG:
+    _orig_resolve_voice = openai_server.resolve_voice
+
+    def _resolve_voice_tagged(voice_name: str) -> dict:
+        return _retarget_embeddings(_orig_resolve_voice(voice_name))
+
+    openai_server.resolve_voice = _resolve_voice_tagged
+
+
 def _do_warmup():
     """Run one short generation to compile CUDA graphs before serving requests."""
     model = openai_server.tts_model
@@ -77,6 +117,7 @@ def _precompute_all_embeddings():
         return
         
     for voice_name, voice_cfg in list(voices.items()):
+        _retarget_embeddings(voice_cfg)
         # skip if already precomputed
         spk_emb_path = voice_cfg.get("speaker_embeddings") or voice_cfg.get("speaker embeddings")
         if spk_emb_path and os.path.isfile(spk_emb_path):
@@ -132,6 +173,11 @@ async def list_audio_voices():
 async def list_audio_models():
     return _models_response
 
+@openai_server.app.get('/voices')
+@openai_server.app.get('/v1/voices')
+async def list_voices():
+    return _models_response
+
 # SillyTavern speaker endpoint
 @openai_server.app.get('/speakers')
 async def get_speakers():

config/run_voicedesign_server.py

@@ -392,6 +392,12 @@ async def list_audio_models():
     _reload_voices_if_changed()
     return _models_response
 
+@app.get("/voices")
+@app.get("/v1/voices")
+async def list_voices():
+    _reload_voices_if_changed()
+    return _models_response
+
 @app.get("/speakers")
 async def get_speakers():
     _reload_voices_if_changed()

docker/docker-compose.portainer-0.6b.yml

@@ -0,0 +1,161 @@
+# ─────────────────────────────────────────────────────────────────────────────
+#  Qwen3-TTS GPU Stack
+#
+#  Ports:
+#    8020 -> Voice clone, OpenAI-compatible /v1/audio/speech 
+#    8021 -> VoiceDesign model for prompt-designed voices
+#    8022 -> CustomVoice model
+#    8023 -> Low-latency streaming voice clone endpoint 
+#
+#  Container Name	            RAM Usage	GPU VRAM Usage
+#  faster-qwen3-tts-voiceclone	~2.72 GiB	5327 MiB (~5.2 GiB)
+#  faster-qwen3-tts-customvoice	~2.88 GiB	4683 MiB (~4.6 GiB)
+#  faster-qwen3-tts-voicedesign	~2.90 GiB	4747 MiB (~4.6 GiB)
+#  faster-qwen3-tts-streaming	~2.54 GiB	5659 MiB (~5.5 GiB)
+#
+#  Voice files:
+#    The voice clone and streaming services scan active voices from:
+#    home/sparky/Media/_Sounds/TTS_Voices/active_voices
+#
+#  Portainer note:
+#    Set HF_TOKEN in the stack environment if the models ever need Hugging Face access.
+# ─────────────────────────────────────────────────────────────────────────────
+
+services:
+  # Standard voice cloning backend used by TTS Voice Creator and other OpenAI-compatible clients.
+  faster-qwen3-tts-voiceclone:
+    image: martinb78/faster-qwen3-tts-dgx-spark:latest
+    container_name: tts-faster-qwen3-tts-voiceclone
+    restart: unless-stopped
+    runtime: nvidia
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=all
+      - HF_TOKEN=${HF_TOKEN}
+      - EMBED_TAG=1.7b
+    ports:
+      - "8020:8000"
+    volumes:
+      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-Base:/models/Qwen3-TTS:ro
+      - /home/sparky/Docker/tts-dgx-spark-faster-qwen3-tts/config:/config:rw
+      - /home/sparky/Media/_Sounds/TTS_Voices/active_voices:/voices:rw
+    command: >
+      /bin/bash -c "
+      python3 /config/generate_voices.py &&
+      python3 /config/run_server.py
+      --model /models/Qwen3-TTS
+      --voices /config/voices.json
+      --port 8000
+      --max-seq-len 4096
+      "
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    networks:
+      - dgx_net
+
+  # VoiceDesign backend: creates speech from a descriptive voice prompt instead of a reference clip.
+  faster-qwen3-tts-voicedesign:
+    image: martinb78/faster-qwen3-tts-dgx-spark:latest
+    container_name: tts-faster-qwen3-tts-voicedesign
+    restart: unless-stopped
+    runtime: nvidia
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=all
+      - HF_TOKEN=${HF_TOKEN}
+    ports:
+      - "8021:8000"
+    volumes:
+      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-VoiceDesign:/models/Qwen3-TTS-VoiceDesign:ro
+      - /home/sparky/Docker/tts-dgx-spark-faster-qwen3-tts/config:/config:rw
+    command: >
+      /bin/bash -c "
+      python3 /config/run_voicedesign_server.py
+      --model /models/Qwen3-TTS-VoiceDesign
+      --voices /config/voicedesign_voices.json
+      --port 8000
+      --max-seq-len 2048
+      "
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    networks:
+      - dgx_net
+
+  # CustomVoice backend: keeps the separate CustomVoice model available on port 8022.
+  faster-qwen3-tts-customvoice:
+    image: martinb78/faster-qwen3-tts-dgx-spark:latest
+    container_name: tts-faster-qwen3-tts-customvoice
+    restart: unless-stopped
+    runtime: nvidia
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=all
+      - HF_TOKEN=${HF_TOKEN}
+    ports:
+      - "8022:8000"
+    volumes:
+      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-CustomVoice:/models/Qwen3-TTS-CustomVoice:ro
+      - /home/sparky/Docker/tts-dgx-spark-faster-qwen3-tts/config:/config:rw
+    command: >
+      /bin/bash -c "
+      python3 /config/run_customvoice_server.py
+      --model /models/Qwen3-TTS-CustomVoice
+      --voices /config/customvoice_voices.json
+      --port 8000
+      --max-seq-len 2048
+      "
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    networks:
+      - dgx_net
+
+  # Streaming voice clone backend: same active voices as 8020, but streams WAV chunks while generating.
+  faster-qwen3-tts-streaming:
+    image: martinb78/faster-qwen3-tts-dgx-spark:latest-streaming
+    container_name: tts-faster-qwen3-tts-streaming
+    restart: unless-stopped
+    runtime: nvidia
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=all
+      - HF_TOKEN=${HF_TOKEN}
+      - EMBED_TAG=0.6b
+    ports:
+      - "8023:8000"
+    volumes:
+      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-0.6B-Base:/models/Qwen3-TTS:ro
+      - /home/sparky/Docker/tts-dgx-spark-faster-qwen3-tts/config:/config:rw
+      - /home/sparky/Media/_Sounds/TTS_Voices/active_voices:/voices:rw
+    command: >
+      /bin/bash -c "
+      python3 /config/generate_voices.py &&
+      python3 /config/run_server.py
+      --model /models/Qwen3-TTS
+      --voices /config/voices.json
+      --port 8000
+      --max-seq-len 2048
+      "
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    networks:
+      - dgx_net
+
+networks:
+  dgx_net:
+    external: true