Add 60db TTS provider (Hindi/Indian voices) — live-API-verified

.env.example

@@ -52,3 +52,9 @@
 # ElevenLabs: Premium cloud TTS (pay-per-character, optional)
 # ELEVENLABS_API_KEY=your_api_key_here
 # ELEVENLABS_VOICE_ID=your_voice_id_here
+#
+# 60db: Premium cloud TTS (https://60db.ai), used via --provider 60db
+# Get a key at https://60db.ai. VOICE_ID is optional (falls back to the
+# 60db default voice; list yours with: python tools/sixtydb_tts.py --list-voices)
+# SIXTYDB_API_KEY=sk_live_your_key
+# SIXTYDB_VOICE_ID=your_voice_id_here

CLAUDE.md

@@ -129,17 +129,45 @@ Utility tools work on any video file without requiring a project structure.
 
 ### Voiceover Generation
 
+Three TTS providers share one `voiceover.py` interface (`--provider`):
+**elevenlabs** (default), **qwen3** (self-hosted, free), and **60db** (premium cloud).
+Voice settings (`--stability`, `--similarity`, `--speed`) use a **unified 0-1 scale**
+across all providers — for 60db they are auto-converted to its native 0-100 scale.
+
 ```bash
-# Per-scene generation (recommended)
+# Per-scene generation (recommended, ElevenLabs default)
 python tools/voiceover.py --scene-dir public/audio/scenes --json
 
 # Using Qwen3-TTS (self-hosted, free alternative to ElevenLabs)
 python tools/voiceover.py --provider qwen3 --tone warm --scene-dir public/audio/scenes --json
 
+# Using 60db (premium cloud TTS — needs SIXTYDB_API_KEY)
+python tools/voiceover.py --provider 60db --scene-dir public/audio/scenes --json
+python tools/voiceover.py --provider 60db --voice-id <uuid> --stability 0.6 --script SCRIPT.md --output out.mp3
+
 # Single file (legacy)
 python tools/voiceover.py --script SCRIPT.md --output out.mp3
 ```
 
+#### 60db (standalone)
+
+`tools/sixtydb_tts.py` is the dedicated 60db tool (counterpart to `qwen3_tts.py`).
+It exposes a `generate_audio()` used by `voiceover.py` and `redub.py`, plus a CLI.
+Three transports all produce a finished audio file: `synthesize` (REST, default),
+`stream` (NDJSON), and `websocket` (realtime; needs `pip install websocket-client`).
+
+```bash
+python tools/sixtydb_tts.py --text "Hello world" --output hello.mp3
+python tools/sixtydb_tts.py --text "Hello" --transport stream --output hello.mp3
+python tools/sixtydb_tts.py --list-voices          # GET /myvoices
+```
+
+Config: `SIXTYDB_API_KEY` (required), `SIXTYDB_VOICE_ID` (optional — falls back to
+60db's default voice). Brands carry a `sixtydb` block in `voice.json` (voiceId +
+settings). `redub.py --tts-provider 60db` uses 60db for the new voice while
+transcription stays on ElevenLabs Scribe (60db has no STT); in `--sync` mode the
+60db output is run back through Scribe to recover word timestamps.
+
 ### Timing Sync (after voiceover)
 
 ```bash

_internal/toolkit-registry.json

@@ -181,11 +181,18 @@
   "tools": {
     "voiceover": {
       "path": "tools/voiceover.py",
-      "description": "Generate TTS voiceovers using ElevenLabs or Qwen3-TTS",
+      "description": "Generate TTS voiceovers using ElevenLabs, Qwen3-TTS, or 60db",
       "usage": "python tools/voiceover.py --script SCRIPT.md --output out.mp3",
+      "options": {
+        "provider": "TTS provider: elevenlabs (default), qwen3, 60db",
+        "transport": "60db API transport: synthesize (default), stream, websocket",
+        "no-enhance": "Disable 60db audio enhancement (on by default)",
+        "stability": "Voice stability 0-1 (unified scale; auto-converted to 0-100 for 60db)",
+        "similarity": "Similarity 0-1 (unified scale; auto-converted to 0-100 for 60db)"
+      },
       "status": "stable",
       "created": "2025-12-08",
-      "updated": "2026-02-19"
+      "updated": "2026-06-08"
     },
     "music": {
       "path": "tools/music.py",
@@ -487,6 +494,44 @@
       "created": "2026-02-19",
       "updated": "2026-02-19"
     },
+    "sixtydb_tts": {
+      "path": "tools/sixtydb_tts.py",
+      "description": "Generate speech using 60db cloud TTS - REST, streaming, and websocket transports",
+      "usage": "python tools/sixtydb_tts.py --text \"Hello\" --output hello.mp3",
+      "status": "beta",
+      "category": "audio-generation",
+      "backend": "60db",
+      "requires": "60db API key",
+      "options": {
+        "voice-id": "60db voice UUID (defaults to SIXTYDB_VOICE_ID or 60db default voice)",
+        "stability": "Voice stability 0-1 (auto-converted to 0-100)",
+        "similarity": "Similarity 0-1 (auto-converted to 0-100)",
+        "speed": "Speech speed 0.5-2.0",
+        "no-enhance": "Disable 60db audio enhancement (on by default)",
+        "output-format": "Audio format: mp3 (default), wav, ogg, flac (synthesize transport)",
+        "transport": "API transport: synthesize (default), stream, websocket",
+        "sample-rate": "Websocket sample rate: 8000, 16000, 24000 (default), 48000",
+        "list-voices": "List your 60db voices via GET /myvoices"
+      },
+      "transports": [
+        "synthesize",
+        "stream",
+        "websocket"
+      ],
+      "endpoints": {
+        "synthesize": "https://api.60db.ai/tts-synthesize",
+        "stream": "https://api.60db.ai/tts-stream",
+        "voices": "https://api.60db.ai/myvoices",
+        "websocket": "wss://api.60db.ai/ws/tts"
+      },
+      "envVars": [
+        "SIXTYDB_API_KEY",
+        "SIXTYDB_VOICE_ID"
+      ],
+      "estimatedCost": "$0.00002 per character ($0.01 minimum per request)",
+      "created": "2026-06-08",
+      "updated": "2026-06-08"
+    },
     "sync_timing": {
       "path": "tools/sync_timing.py",
       "description": "Sync scene durationSeconds in Remotion config with actual audio durations",
@@ -1025,6 +1070,7 @@
   },
   "config": {
     "voiceId": "YOUR_VOICE_ID_HERE",
+    "sixtydbVoiceId": null,
     "defaultFps": 30,
     "defaultResolution": {
       "width": 1920,

brands/default/voice.json

@@ -14,5 +14,14 @@
     "tone": "",
     "instruct": "",
     "clone": null
+  },
+  "sixtydb": {
+    "voiceId": "YOUR_VOICE_ID_HERE",
+    "settings": {
+      "stability": 0.85,
+      "similarity": 0.95,
+      "speed": 1.0,
+      "enhance": true
+    }
   }
 }

tools/config.py

@@ -51,6 +51,30 @@ def get_elevenlabs_api_key() -> str | None:
     return os.getenv("ELEVENLABS_API_KEY")
 
 
+def get_sixtydb_api_key() -> str | None:
+    """Get 60db API key from environment."""
+    from dotenv import load_dotenv
+    load_dotenv()
+    return os.getenv("SIXTYDB_API_KEY")
+
+
+def get_sixtydb_voice_id() -> str | None:
+    """Get the 60db voice ID from env var, falling back to the registry.
+
+    Returns None if neither is set — callers fall back to the documented
+    60db default voice.
+    """
+    from dotenv import load_dotenv
+    load_dotenv()
+
+    voice_id = os.getenv("SIXTYDB_VOICE_ID")
+    if voice_id and voice_id != "your_voice_id_here":
+        return voice_id
+
+    registry = load_registry()
+    return registry.get("config", {}).get("sixtydbVoiceId")
+
+
 def get_default_output_dir(project_path: str | None = None) -> Path:
     """Get default audio output directory for a project."""
     if project_path: