Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions .env.example
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,19 @@ TAVILY_API_KEY=
# OPENREELS_LLM_MODEL=llama3:8b
# OPENREELS_LLM_API_KEY=

# Optional: 60db cloud provider (LLM + TTS + alignment)
# Adds these CLI flags:
# --provider 60db
# --tts-provider 60db (sync REST /tts-synthesize)
# --tts-provider 60db-stream (NDJSON /tts-stream)
# --tts-provider 60db-ws (realtime WebSocket /ws/tts)
# SIXTYDB_API_KEY=sk_live_...
# SIXTYDB_API_BASE=https://api.60db.ai
# SIXTYDB_LLM_MODEL=60db-tiny
# SIXTYDB_TTS_VOICE_ID=fbb75ed2-975a-40c7-9e06-38e30524a9a1
# Swap local Whisper alignment for 60db /stt (no GPU needed):
# SIXTYDB_USE_CLOUD_ALIGNER=true

# Optional: Stock footage (free, but requires registration)
# Pexels: https://www.pexels.com/api/
PEXELS_API_KEY=
Expand Down
32 changes: 30 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -82,9 +82,9 @@ Mix and match providers or go all-in on one ecosystem:

| Capability | Providers |
|-----------|-----------|
| **LLM** | Anthropic Claude, OpenAI GPT, Google Gemini, OpenRouter (300+ models), any OpenAI-compatible endpoint |
| **LLM** | Anthropic Claude, OpenAI GPT, Google Gemini, OpenRouter (300+ models), 60db, any OpenAI-compatible endpoint |
| **Search** | Native (provider built-in), Tavily, or parametric knowledge |
| **TTS** | ElevenLabs, Inworld, OpenAI TTS, Gemini TTS, Kokoro (free, local) |
| **TTS** | ElevenLabs, Inworld, OpenAI TTS, Gemini TTS, Kokoro (free, local), 60db (sync REST + NDJSON stream + WebSocket) |
| **Images** | Gemini Imagen, OpenAI DALL-E |
| **Video** | Google Veo 3.1, fal.ai Kling 2.6 Pro (with cross-provider fallback, negative prompts, structured cinematography prompts) |
| **Music** | Google Lyria 3 Pro (AI-generated, $0.08/track), Bundled library (free) |
Expand All @@ -94,6 +94,34 @@ Mix and match providers or go all-in on one ecosystem:

**Zero-cost voiceover:** `--provider local` uses Kokoro for free local TTS. No API key needed.

### 60db cloud provider

This fork adds [60db](https://docs.60db.ai) as a first-class provider. One `SIXTYDB_API_KEY` unlocks LLM + 3 TTS surfaces + optional cloud STT alignment.

| Flag | Surface | Wire |
|---|---|---|
| `--provider 60db` | LLM | `POST https://api.60db.ai/v1/chat/completions` (default model: `60db-tiny`) |
| `--tts-provider 60db` | TTS sync REST | `POST /tts-synthesize` — one-shot mp3 + Whisper alignment |
| `--tts-provider 60db-stream` | TTS NDJSON | `POST /tts-stream` — chunked mp3 + Whisper alignment |
| `--tts-provider 60db-ws` | TTS WebSocket | `wss://api.60db.ai/ws/tts` — LINEAR16 PCM → WAV → MP3 transcoded via ffmpeg |
| `SIXTYDB_USE_CLOUD_ALIGNER=true` | Word alignment | Swap local Whisper for `POST /stt` (no GPU needed) |

Env:

```env
SIXTYDB_API_KEY=sk_live_...
SIXTYDB_API_BASE=https://api.60db.ai # optional
SIXTYDB_LLM_MODEL=60db-tiny # optional
SIXTYDB_TTS_VOICE_ID=fbb75ed2-975a-40c7-9e06-38e30524a9a1 # optional
SIXTYDB_USE_CLOUD_ALIGNER=true # optional, swap WhisperAligner
```

Example — go end-to-end on 60db:

```bash
openreels "the dawn of stoicism" --provider 60db --tts-provider 60db
```

## Quickstart

### Web UI (recommended)
Expand Down
2 changes: 2 additions & 0 deletions package.json
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
"@types/node": "^25.5.0",
"@types/react": "^19.2.14",
"@types/react-dom": "^19.2.3",
"@types/ws": "^8.5.13",
"react": "^19.2.4",
"react-dom": "^19.2.4",
"remotion": "^4.0.441",
Expand Down Expand Up @@ -69,6 +70,7 @@
"openai": "^6.33.0",
"p-limit": "^7.3.0",
"wavefile": "^11.0.0",
"ws": "^8.18.0",
"zod": "^4.3.6"
}
}
52 changes: 51 additions & 1 deletion src/cli/args.test.ts
Original file line number Diff line number Diff line change
@@ -1,5 +1,55 @@
import { describe, expect, it } from "vitest";
import { afterEach, describe, expect, it } from "vitest";
import type { CLIOptions } from "./args.js";
import { parseArgs } from "./args.js";

describe("parseArgs with 60db", () => {
const originalArgv = process.argv;

afterEach(() => {
process.argv = originalArgv;
});

it("accepts --provider 60db", () => {
process.argv = ["node", "openreels", "test topic", "--provider", "60db"];
const opts = parseArgs();
expect(opts.provider).toBe("60db");
expect(opts.topic).toBe("test topic");
});

it("accepts --tts-provider 60db", () => {
process.argv = ["node", "openreels", "test topic", "--tts-provider", "60db"];
const opts = parseArgs();
expect(opts.ttsProvider).toBe("60db");
});

it("accepts --tts-provider 60db-stream", () => {
process.argv = ["node", "openreels", "test topic", "--tts-provider", "60db-stream"];
const opts = parseArgs();
expect(opts.ttsProvider).toBe("60db-stream");
});

it("accepts --tts-provider 60db-ws", () => {
process.argv = ["node", "openreels", "test topic", "--tts-provider", "60db-ws"];
const opts = parseArgs();
expect(opts.ttsProvider).toBe("60db-ws");
});

it("accepts the documented 60db end-to-end flags together", () => {
process.argv = [
"node",
"openreels",
"the dawn of stoicism",
"--provider",
"60db",
"--tts-provider",
"60db",
];
const opts = parseArgs();
expect(opts.provider).toBe("60db");
expect(opts.ttsProvider).toBe("60db");
expect(opts.topic).toBe("the dawn of stoicism");
});
});

describe("CLIOptions type", () => {
it("includes yes field for non-interactive mode", () => {
Expand Down
12 changes: 11 additions & 1 deletion src/cli/args.ts
Original file line number Diff line number Diff line change
Expand Up @@ -96,6 +96,7 @@ export function parseArgs(): CLIOptions {
"openai-compatible",
"google",
"local",
"60db",
])
.default("anthropic"),
)
Expand All @@ -120,7 +121,16 @@ export function parseArgs(): CLIOptions {
)
.addOption(
new Option("--tts-provider <provider>", "TTS provider")
.choices(["elevenlabs", "inworld", "kokoro", "gemini-tts", "openai-tts"])
.choices([
"elevenlabs",
"inworld",
"kokoro",
"gemini-tts",
"openai-tts",
"60db",
"60db-stream",
"60db-ws",
])
.default("elevenlabs"),
)
.option(
Expand Down
32 changes: 32 additions & 0 deletions src/cli/cost-estimator.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -184,6 +184,31 @@ describe("estimateCost", () => {
expect(geminiLlm.llmCost).toBeGreaterThan(0);
});

it("uses 60db LLM pricing when llmProvider is 60db", () => {
const score = makeScore([{ visual_type: "ai_image", script_line: "Test" }]);
const result = estimateCost(score, "gemini", "elevenlabs", undefined, "60db");
// 60db chat is $0.50/1M tokens in and out (60db.ai/pricing):
// research + creative director + critic + 1 image prompt
// = 10,800 input + 3,700 output tokens = 14,500 * $0.50/1M = $0.00725
expect(result.llmCost).toBeGreaterThan(0);
expect(result.llmCost).toBeCloseTo(0.00725, 5);
});

it("uses 60db TTS pricing when ttsProvider is 60db", () => {
const score = makeScore([{ visual_type: "text_card", script_line: "Hello world" }]);
const result = estimateCost(score, "gemini", "60db");
// 60db TTS is $0.02/1K chars (60db.ai/pricing): 11 chars * $0.00002
expect(result.ttsCost).toBeCloseTo(11 * 0.00002, 8);
});

it("uses 60db TTS pricing for stream and ws variants", () => {
const score = makeScore([{ visual_type: "text_card", script_line: "Hello world" }]);
const stream = estimateCost(score, "gemini", "60db-stream");
const ws = estimateCost(score, "gemini", "60db-ws");
expect(stream.ttsCost).toBeCloseTo(11 * 0.00002, 8);
expect(ws.ttsCost).toBeCloseTo(11 * 0.00002, 8);
});

it("uses zero-cost fallback for unknown providers (openrouter)", () => {
const score = makeScore([{ visual_type: "ai_image", script_line: "Test" }]);
const result = estimateCost(score, "gemini", "elevenlabs", undefined, "openrouter");
Expand Down Expand Up @@ -324,6 +349,13 @@ describe("computeActualLLMCost", () => {
expect(gemini.llmCost).toBeGreaterThan(0);
});

it("uses 60db pricing in computeActualLLMCost", () => {
const usages: LLMUsage[] = [{ inputTokens: 1_000_000, outputTokens: 1_000_000 }];
const result = computeActualLLMCost(usages, { aiImages: 0, ttsCharacters: 0 }, "60db");
// $0.50/1M in + $0.50/1M out = $1.00
expect(result.llmCost).toBeCloseTo(1.0, 5);
});

it("uses zero-cost fallback for unknown LLM provider (openrouter)", () => {
const usages: LLMUsage[] = [{ inputTokens: 1_000_000, outputTokens: 1_000_000 }];
const result = computeActualLLMCost(usages, { aiImages: 0, ttsCharacters: 0 }, "openrouter");
Expand Down
7 changes: 7 additions & 0 deletions src/cli/cost-estimator.ts
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,10 @@ const LLM_PRICING = {
perInputToken: 0.1 / 1_000_000, // $0.10 per 1M input tokens (Gemini 2.5 Flash)
perOutputToken: 0.4 / 1_000_000, // $0.40 per 1M output tokens (Gemini 2.5 Flash)
},
"60db": {
perInputToken: 0.5 / 1_000_000, // $0.50 per 1M input tokens (60db chat, 60db.ai/pricing)
perOutputToken: 0.5 / 1_000_000, // $0.50 per 1M output tokens (60db chat, 60db.ai/pricing)
},
};

const PRICING = {
Expand All @@ -73,6 +77,9 @@ const PRICING = {
kokoro: 0, // Free — local inference
"gemini-tts": 0.00002, // ~$0.02/1K chars (Gemini 2.5 Flash TTS: $0.50/1M text in + $10/1M audio out, ~2 audio tokens per char)
"openai-tts": 0.00005, // ~$0.05 per 1K chars (gpt-4o-mini-tts: $0.60/1M text tokens in + $12/1M audio tokens out)
"60db": 0.00002, // $0.02 per 1K chars (60db TTS, 60db.ai/pricing)
"60db-stream": 0.00002, // $0.02 per 1K chars (60db TTS stream, 60db.ai/pricing)
"60db-ws": 0.00002, // $0.02 per 1K chars (60db TTS WebSocket, 60db.ai/pricing)
} satisfies Record<TTSProviderKey, number>,
// Gemini 3.1 Flash Image Preview: $60/M output tokens
// 1080x1920 (>1024px, <=2048px) = 1680 tokens = $0.101/image
Expand Down
87 changes: 87 additions & 0 deletions src/cli/validate-env.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -292,4 +292,91 @@ describe("validateEnv", () => {
delete process.env["ELEVENLABS_API_KEY"];
delete process.env["GOOGLE_API_KEY"];
});

it("requires SIXTYDB_API_KEY when --provider 60db", () => {
delete process.env.SIXTYDB_API_KEY;
process.env.ELEVENLABS_API_KEY = "test";
process.env.GOOGLE_API_KEY = "test";

validateEnv({ provider: "60db", ttsProvider: "elevenlabs", imageProvider: "gemini" });

expect(exitSpy).toHaveBeenCalledWith(1);
const output = errorSpy.mock.calls.flat().join("");
expect(output).toContain("SIXTYDB_API_KEY");

delete process.env.ELEVENLABS_API_KEY;
delete process.env.GOOGLE_API_KEY;
});

it("requires SIXTYDB_API_KEY when --tts-provider 60db", () => {
delete process.env.SIXTYDB_API_KEY;
process.env.ANTHROPIC_API_KEY = "test";
process.env.GOOGLE_API_KEY = "test";

validateEnv({ provider: "anthropic", ttsProvider: "60db", imageProvider: "gemini" });

expect(exitSpy).toHaveBeenCalledWith(1);
const output = errorSpy.mock.calls.flat().join("");
expect(output).toContain("SIXTYDB_API_KEY");

delete process.env.ANTHROPIC_API_KEY;
delete process.env.GOOGLE_API_KEY;
});

it("requires SIXTYDB_API_KEY when --tts-provider 60db-stream", () => {
delete process.env.SIXTYDB_API_KEY;
process.env.ANTHROPIC_API_KEY = "test";
process.env.GOOGLE_API_KEY = "test";

validateEnv({ provider: "anthropic", ttsProvider: "60db-stream", imageProvider: "gemini" });

expect(exitSpy).toHaveBeenCalledWith(1);
const output = errorSpy.mock.calls.flat().join("");
expect(output).toContain("SIXTYDB_API_KEY");

delete process.env.ANTHROPIC_API_KEY;
delete process.env.GOOGLE_API_KEY;
});

it("requires SIXTYDB_API_KEY when --tts-provider 60db-ws", () => {
delete process.env.SIXTYDB_API_KEY;
process.env.ANTHROPIC_API_KEY = "test";
process.env.GOOGLE_API_KEY = "test";

validateEnv({ provider: "anthropic", ttsProvider: "60db-ws", imageProvider: "gemini" });

expect(exitSpy).toHaveBeenCalledWith(1);
const output = errorSpy.mock.calls.flat().join("");
expect(output).toContain("SIXTYDB_API_KEY");

delete process.env.ANTHROPIC_API_KEY;
delete process.env.GOOGLE_API_KEY;
});

it("passes when --provider 60db and SIXTYDB_API_KEY is set", () => {
process.env.SIXTYDB_API_KEY = "test";
process.env.GOOGLE_API_KEY = "test";

validateEnv({ provider: "60db", ttsProvider: "60db", imageProvider: "gemini" });

expect(exitSpy).not.toHaveBeenCalled();

delete process.env.SIXTYDB_API_KEY;
delete process.env.GOOGLE_API_KEY;
});

it("does not require SIXTYDB_API_KEY when 60db is not used", () => {
process.env.ANTHROPIC_API_KEY = "test";
process.env.ELEVENLABS_API_KEY = "test";
process.env.GOOGLE_API_KEY = "test";
delete process.env.SIXTYDB_API_KEY;

validateEnv({ provider: "anthropic", ttsProvider: "elevenlabs", imageProvider: "gemini" });

expect(exitSpy).not.toHaveBeenCalled();

delete process.env.ANTHROPIC_API_KEY;
delete process.env.ELEVENLABS_API_KEY;
delete process.env.GOOGLE_API_KEY;
});
});
7 changes: 7 additions & 0 deletions src/cli/validate-env.ts
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,13 @@ export function validateEnv(opts: {
signupUrl: "https://openrouter.ai/",
required: opts.provider === "openrouter",
},
{
key: "SIXTYDB_API_KEY",
provider: "60db (LLM/TTS)",
signupUrl: "https://60db.ai",
required:
opts.provider === "60db" || ["60db", "60db-stream", "60db-ws"].includes(opts.ttsProvider),
},
{
key: "TAVILY_API_KEY",
provider: "Tavily (Web Search)",
Expand Down
Loading