이 페이지는 아직 한국어로 번역되지 않아서 영어판을 보여 드려요.
Comparison
CastDub as an ElevenLabs alternative for multi-voice scripts
ElevenLabs is very good at what it is built for. If your script has six people in it and you are running the tool once per person, this page is about whether a casting-shaped tool removes that work — and about the four cases where it does not.
Checked:
We are a competitor of ElevenLabs, so treat everything below as interested testimony and check the links. Every ElevenLabs fact on this page was read off their own pricing page or their own documentation on 2026-09-21, and the URL is printed next to it.
The short version: ElevenLabs is a voice platform with an excellent cloning story and, in their own words on the Text to Dialogue documentation, “no limit to the number of speakers in a dialogue”. CastDub is a smaller thing — a production tool for scripts that already have speakers in them. Which of those you want depends on questions that have nothing to do with which demo reel sounds better.
What we could verify
| CastDub | ElevenLabs | Typecast | |
|---|---|---|---|
| Several characters from one pasted script? | Yes, and it is the whole product: paste a script, it splits the lines, works out who is speaking and gives each speaker one of 40 library characters. Up to 10 distinct base voices in one project. | “There is no limit to the number of speakers in a dialogue” (Text to Dialogue API, Eleven v3, 2,000 characters per request); in Studio you can “assign multiple voices to a single paragraph”. (source) | Not stated on the pages we checked. (source) |
| Direct emotion line by line? | Per line on Pro; on every plan each character carries a default emotion. 7 emotions, performed by the line rather than approximated with pitch and speed. | Bracketed audio tags inside the text, e.g. [sad], which “influence the delivery of the dialogue” on Eleven v3. (source) | Pro: “Fine-tune voices with emotion controls” and “Advanced voice controls including intonation”; Plus: “Control voice speed”. (source) |
| One audio file per character (stems)? | Pro only: a ZIP with the mix plus one full-length MP3 per character. | Not stated on their Studio documentation; downloads are described as “MP3 or WAV”. (source) | Not stated on their site. (source) |
| Subtitles? | Plus and Pro: an SRT file, and exporting it costs no credits. | Studio captions are “generated automatically and can be customized with templates”; an SRT file is not stated. (source) | Not stated on their site; the pricing page lists “HD (720p) video exports”. (source) |
| Clone your own voice? | No. Voice cloning is not live here. If cloning your own voice is the point, we are the wrong tool today. | “Instant Voice Cloning” from Starter; “Professional Voice Cloning” from Creator. (source) | Basic: “Instant Cloning (1 slot)”; Plus: “Professional Cloning (1 slot in total)”; Pro: 2 slots; Business: 10 slots. (source) |
| Free plan | Yes: 4,500 lifetime download credits (about 11 minutes of finished English audio), 30 synthesised lines per 24 hours, 2 cast members per project. Generating and previewing never costs credits on any plan. | Free at $0 with “10k credits per month” and “3 Projects in Studio”. (source) | “Voice generation & playback Unlimited”, “Lifetime download credits 3,000 credits (~5 mins)”, and “Attribution is required for all content downloaded on the Free plan”. (source) |
| Commercial use on the free plan | No. Free is personal, non-commercial use. A commercial licence starts at Basic, and the open beta does not change that. | “Commercial License” starts at Starter, so not on Free. (source) | Commercial licence starts at Basic; free downloads require attribution. (source) |
| Entry paid price | $5/month for Basic once payment is switched on. Nothing is being charged during the open beta, while every account runs at Pro-level features. | Starter $6/month for “30k credits per month”; Creator $11/month for “121k credits per month”. (source) | Basic $5/month, Plus $19/month, Pro $29/month, Business $69/month. (source) |
| Languages | 9: English, Chinese, Japanese, Korean, Spanish, Portuguese, French, German, Russian. Every base voice speaks all of them. Regional accents cannot be chosen outside English, and we do not promise them. | “74” languages listed against the paid tiers. (source) | “35+ languages” on their home page. (source) |
Checked 2026-09-21. Prices are the monthly figures printed on each company's own page in US dollars; annual and promotional rates differ and change often.
“Not stated on their site” means exactly that — we opened the pages listed below and the fact was not on them. It is not a claim that the feature is missing.
The CastDub column is generated from the same code that runs the product (lib/plans.ts and the casting code), so it cannot drift away from what you actually get.
Can it voice several characters in one script?
Both can, in different shapes. ElevenLabs' Text to Dialogue API “creates natural sounding expressive dialogue from text using the Eleven v3 model”, and their documentation states plainly that “There is no limit to the number of speakers in a dialogue”, with the caveat to keep a request at or below 2,000 characters. In their Studio product, the documentation says you can “assign multiple voices to a single paragraph” by selecting text and changing the voice from a drop-down.
CastDub starts from the other end. You paste the whole script — a screenplay, a “NAME: line” transcript, prose with speech tags, or the dash dialogue used in Spanish, French, Portuguese and Russian — and the tool works out who the speakers are, makes a character for each one, and casts each character from a library of 40. Within one project, two characters never share a base voice until that gender's pool is exhausted, so a four-hander stays legible without you managing anything.
The honest limit on our side: there are 10 base voices (4 female, 5 male, 1 neutral), so a scene with more than 10 speakers will have people sharing a voice, distinguished only by acting direction. If your cast list is longer than that, know it before you start rather than after.
Is there a free plan, and what can you take away from it?
ElevenLabs' pricing page lists a Free tier at $0 with “10k credits per month” and “3 Projects in Studio”, then Starter at $6 for 30k credits, Creator at $11 (with a first month at $6) for 121k credits, Pro at $99, Scale at $299 and Business at $990. The same page puts the “Commercial License” at Starter, which means the free tier is not for commercial work.
CastDub's free tier is shaped differently on purpose: 4,500 lifetime download credits — about 11 minutes of finished English audio — and credits are only spent when you download. Generating and previewing costs nothing on any plan; there is a synthesis ceiling of 30 lines per 24 hours instead, so you can re-listen to a scene twenty times while you cut it without watching a meter.
One thing to know before you sign up: we have not switched payment on yet. During the open beta every account runs with Pro-level features and nothing is charged. The commercial licence is a term rather than a switch, so it does not open up with it — free use stays personal.
Can you direct emotion line by line?
ElevenLabs does this through the text itself. Their Text to Dialogue documentation describes “non-speech audio events” written in square brackets inside the input — emotions such as [sad], events such as [applause] — which “influence the delivery of the dialogue” on the Eleven v3 model. It is expressive and it composes well with a script, because the direction lives in the script.
CastDub does it with a control on the line. Each character carries a default emotion on every plan; on Pro you can override any single line with one of 7 emotions, and Plus and Pro add a five-step speed control from 0.75× to 1.25×. The emotion is genuinely acted for that line rather than faked with a filter, which also means re-generating a line gives a slightly different take — same voice, new performance. When a read is not right, the fix is to press it again.
Neither approach wins in the abstract: tags travel with the text into other tools, a control is better for auditioning four readings of one line.
Does it export stems and subtitles?
This is where we differ most, and where you should check us rather than trust us. On Pro, CastDub exports a ZIP containing the mix plus one full-length MP3 per character, time-aligned, so you can score a scene properly in a DAW instead of ducking music under a single dialogue track. Plus and Pro also export an SRT, and the subtitle export does not cost credits.
On the ElevenLabs side, their Studio documentation states you can “download as MP3 or WAV”, with quality tied to plan — 128 kbps MP3 on the smaller plans, and 16-bit WAV or 192 kbps MP3 higher up, a WAV option we do not have at all. The same page describes automatic captions that “can be customized with templates for colors, fonts, and placement”. A per-speaker stem export is not stated on the pages we read, which is not the same as saying it does not exist — it means we could not verify it and so we did not put a tick or a cross in that box.
That is the clearest advantage in this section and it is theirs: WAV delivery, which we do not offer at all — everything here is MP3, and that alone can decide it if you deliver to a spec sheet.
Which languages, and how many voices?
ElevenLabs' pricing table lists 74 languages against the paid tiers. That is an order of magnitude past us and it is their page's number, not ours.
CastDub has 9: English, Chinese, Japanese, Korean, Spanish, Portuguese, French, German and Russian. Every one of the 10 base voices speaks all 9, so no language here is a second-class citizen with a thinner voice list. What we will not promise is a regional accent: outside English you get the general accent of the language — Mandarin, Latin American Spanish, Brazilian Portuguese — and you cannot pick a city. We also have not had every language signed off by native reviewers, so the honest instruction is to paste your own lines and listen before you commit a project to us.
If your work is in a language we do not have, coverage beats workflow and the decision is already made.
Can I clone my own voice?
With ElevenLabs, yes, and it is one of the clearest reasons to choose them. Their pricing page places “Instant Voice Cloning” at the Starter tier and “Professional Voice Cloning” at Creator and above.
With CastDub, no. Voice cloning is not live here. When it is, it will come with rules we have already written down — consent from the person recorded, no public figures, never a minor — but a policy is not a feature, and today the answer to “can I use my own voice” is no.
If a cloned voice is the centre of your workflow, that settles this comparison in their favour and nothing else on this page outweighs it.
When you should pick ElevenLabs instead
Four cases, and we think they are common. First, single-narrator work — an audiobook, a documentary VO, a solo podcast: the casting machinery buys you nothing and you would be paying attention for a feature you never touch. Second, cloning, as above. Third, language coverage: 74 against 9 is not a close call if your language is in the gap. Fourth, an existing pipeline — if you have API calls, a render step and a mixing template that work, the cost of switching is higher than it looks from a comparison page.
There is a fifth, quieter case: their scale. Bigger plans, WAV delivery, an API with published limits and a large body of documentation — if you answer to a procurement team, that maturity is worth something we cannot match this year.
Our case is narrow and we would rather state it narrowly: a script with several speakers, currently generated one at a time and assembled by hand, with stems and subtitles needed at the end. That is the hour of work we exist to delete. If that is not your hour, stay where you are.
How this page was written
We make a competing product, so a page like this is marketing whatever we do with it. What we can do is make it checkable. Every claim about ElevenLabs above was read on 2026-09-21 from their own pricing page or their own documentation, the URL sits next to the claim, and where a page did not state something we wrote “not stated on their site” rather than guessing from memory or copying a third-party review.
We also left out the things that comparison tables usually smuggle in: no ticks and crosses, no scores, no judgements about which voices sound better — that one is yours to make with your own script in both tools. There is no row we filled with an opinion.
Our own column is not hand-typed either. The numbers come from the same plan definitions the product enforces, interpolated when this page is built, so if we change a price or a credit allowance and forget this page, the page changes anyway.
If you find a row that is wrong or out of date — vendors reprice without telling their competitors — tell us and we will fix it and move the Checked date. We would rather be corrected than quoted wrongly.
Where each fact came from
Every row above that describes another product came from one of these pages. Open them yourself — vendors change their plans without telling anyone, including us.
- ElevenLabs — Pricing — Free $0 / 10k credits per month with 3 Projects in Studio; Starter $6 / 30k; Creator $11 / 121k; Pro $99 / 600k; Scale $299 / 1.8M; Business $990 / 6M; Commercial License from Starter; Instant Voice Cloning from Starter and Professional Voice Cloning from Creator; 74 languages listed against paid tiers.
- ElevenLabs — Text to Dialogue documentation — “There is no limit to the number of speakers in a dialogue”; bracketed audio tags influence delivery; Eleven v3 only; keep a request at or below 2,000 characters.
- ElevenLabs — Studio product guide — Multiple voices can be assigned within a paragraph; downloads as MP3 or WAV with quality by plan; automatic, template-customisable captions; per-speaker stems not stated.
- Typecast — Pricing — Free $0 with 3,000 lifetime download credits and attribution required; Basic $5, Plus $19, Pro $29, Business $69; emotion controls on Pro; cloning capacity stated per plan.
- Typecast — Home — “700+ AI voices” and “35+ languages”.
자주 묻는 질문
Is CastDub cheaper than ElevenLabs?
Not comparably, because the units differ. Their pricing page prices credits per month from $6; ours charges credits only when you download, at $5/month for Basic and $29/month for Pro, and generating or previewing is free on every plan. The only honest comparison is to take one real script, produce it in both, and look at what each one actually deducted.
Can I move a project from ElevenLabs to CastDub?
Only by pasting the script. There is no import: no .txt, .docx or .srt upload, and no way to bring your ElevenLabs voices or settings over. In practice that is a copy-paste of the script and a re-cast, which takes a couple of minutes for a scene.
Does CastDub have voice cloning like ElevenLabs?
No. It is not live. Their pricing page offers instant cloning from Starter and professional cloning from Creator; we offer neither today, and if cloning is what you need you should use them.
How many speakers can one CastDub project have?
As many as your script has, but only 10 distinct base voices exist, so beyond that characters begin sharing a voice and are told apart by their acting directions alone. For a dense ensemble scene, split it into projects by group of speakers, or accept the doubling deliberately by casting the sharers as far apart in age and manner as you can.
Do I get separate audio tracks per character?
On Pro, yes: a ZIP with the mix plus one full-length MP3 per character and an SRT. On Plus and Pro you get subtitles but a single mixed MP3. We could not verify a per-speaker export on the ElevenLabs pages we read, so check their docs yourself if it is decisive for you.
Which one is better for audio drama?
If your drama is multi-voice, the pipeline question decides it: whether you can re-render one line without rebuilding a scene, and whether you can get stems for the mix. If your drama is a single narrator with occasional quotes, that question never arises and their larger language coverage and cloning are worth more than our casting.
If you are working on one of these
Voices you can cast
Other comparisons
오늘 밤, 첫 장면을 캐스팅해 보세요
장면을 붙여 넣고, CastDub가 인물마다 보이스를 붙이게 하고, 완성된 오디오 드라마로 내보내세요.
무료로 만들어 보기카드 등록 없이. 무료 요금제는 한 번만 주어지는 크레딧이에요.