Products used by Dial
Explore the tech stack and tools that power Dial. See what products Dial uses for development, design, marketing, analytics, and more.
Design & Creative 1
tried this with our own site (getdial.ai) expecting the "type your URL, get a video" flow the tagline promises. what actually happens is the web page hands you a terminal command, npx @videoflow/studio --url ..., that runs the whole thing locally through your own Claude Code or Codex subscription. once I understood that, the pitch made a lot more sense: you're not paying for GPU or rendering time, you're paying for the direction and judgment layer on top of a coding agent you already have. the agent did a genuinely good job reading our unusually structured site rather than just templating our page headings, which is the actual hard part of this problem.
LLMs 1
described a rough workflow in plain English ("route billing questions to billing help, escalate only when the caller explicitly asks for a human") and it generated actual states and transitions from that, no signup or account needed, everything saved locally in the browser. ran the simulation mode (no API key required) with a test message and it correctly matched the right end state with a confidence score and a transition-probability breakdown, which is more transparency than i expected from a free tool. the fact that regression tests and runnable TypeScript export sit right next to the simulator, instead of behind a separate paid tier, is the part that'd make me actually use this instead of just admiring it
Voice AI Tools 1
tested this directly in AI Studio rather than just reading the launch post. zero setup since I already had a Google account logged in, went straight from the playground to generating a speech clip. gave it a line of dialogue with a hard tone shift in the middle (calm to panicked) plus a couple of vocal-burst tags like <gasp>, and it generated a 9-second clip in a few seconds with no fiddling. the tag system (style, expression, per-speaker settings) is more control than I expected from something this fast, and the dual-speaker screenplay mode is a real differentiator versus single-voice TTS APIs where you have to stitch turns together yourself.