A new tool from Vox9 Studios launched today: Captions, live at studio.vox9.io. It's a focused tool for turning a block of text into a narrated, captioned video clip โ the kind of thing you'd use to promote an episode on TikTok, Reels, YouTube Shorts, or just share as a quick voice note that reads itself.
It's built as a separate service so it can move at its own pace without slowing Vox9 itself down. But it shares your Vox9 login โ one click from your dashboard menu and you're in, no second account, no second password.
Worth being honest about why this is going live now: this same code already powers the captions baked into Vox9's own audiobook episodes โ running on full-length stories that span hours. So I know it works. For the trial I've pointed it at Azure instead of ElevenLabs โ about 50ร cheaper at scale, which is what makes it free for members โ but the same code can run on ElevenLabs or any other TTS engine. Proven at long form inside Vox9; now open as a free tool to every member.
โ๏ธ What it does, in a single 4-step flow
- Paste up to 1000 characters of text โ a teaser, a piece of dialogue, a short pitch
- Pick a voice from 15 natural English options (US, UK, Australian, Irish, and Indian English), adjust speed, pitch, and sentence gap to taste
- Tune the caption style โ font, size, position, bold/italic. Live preview shows how it'll look
- Render the video โ HD widescreen (1280ร720) or vertical (720ร1280) for mobile / TikTok / Reels / Shorts
You get an MP3 of the narration, an SRT caption file with sentence-accurate timing, and a captioned MP4 โ all downloadable, all yours. Captions burn into the video over a pure-black background with a small Vox9 watermark in the corner, so the output drops cleanly into CapCut or any editor: set blend mode to Screen, the black disappears, and the captions float over your own visuals.
๐๏ธ The voices
Vox9 Captions uses Microsoft Azure Speech for the narration โ production-quality neural voices, the same engine major podcast networks and audiobook publishers use for short-form content. Quality is excellent for clips up to about a minute; for full-length audiobooks, Vox9 itself still uses ElevenLabs, which is the gold standard for long-form character expressiveness.
Why the split? Cost. Azure is about 50ร cheaper per character than ElevenLabs at equivalent quality for short clips โ which is what lets us offer captions free to every Vox9 member during this trial. The difference would be noticeable across a 90-minute audiobook; for a 30-second clip, it's effectively imperceptible.
๐ How to access it
Open the user menu in the top-right of your Vox9 dashboard and click ๐ฌ Open Captions. A new tab opens, you're signed in automatically (no separate login), and you land directly in the rig ready to go.
You can also visit studio.vox9.io directly โ if you're not signed in via Vox9 first, it'll bounce you back here to handle the auth.
๐ What the trial covers
- 1000 characters per clip โ the only cap. No monthly limits, no per-day quotas, no credits to manage. Use it as often as you like during the trial.
- Free for every Vox9 member โ no payment, no subscription tier, no upsell. If you're signed into Vox9, captions is yours.
- HD widescreen + HD vertical video output. (FHD 1080p is reserved for a later paid tier if demand justifies it.)
- Watermark on every rendered MP4. Universal during the trial. Future paid-tier idea: optional watermark removal.
If real demand emerges for longer clips, the future paid path will be one-time character credit packs โ never a subscription tier. The trial design is deliberate: one offer, one cap, and free.
๐ก What it's for
Some use cases that have come up in early testing:
- A 30-second teaser for your latest chapter to post on Twitter / TikTok
- A vertical-format clip of a dramatic line of dialogue for YouTube Shorts
- Voice memos for co-writers who'd rather hear a scene than read it
- Quick accessibility samples โ running a piece of writing through a clear narrator to spot pacing issues
- "Coming next week" tease videos with the first paragraph of an upcoming episode
If you make something you're proud of, we'd love to see it โ drop a link in the support inbox and we'll consider featuring a few on the hub.
Captions is the headline event today โ a whole new tool, free for every member, with no friction to access. Give it a spin, share what you make, and as always: feedback is the most useful thing you can send us. support@vox9.io.