A robot reading a script. The text-to-speech voices at ElevenLabs certainly sound intelligent as well as natural!

ElevenLabs : 5-Star Tool for Language Work and Study

If you’re a regular reader, you’ll know how impressed I’ve been at ElevenLabs, the text-to-speech creator that stunned the industry when its super-realistic voices were unleashed on the world. Since then, it’s made itself irreplaceable in both my work and study, and it bears spreading the word again: ElevenLabs is a blow-your-socks-off kind of tool for creating spoken audio content.

Professional Projects

In my work developing language learning materials for schools, arranging quality narration used to involve coordinating with agencies and studios — a process that was both time-consuming and costly. We’ve had issues with errors, too, which cost a project time with re-recordings. And that’s not to mention the hassle keeping sections up-to-date. Removing ‘stereo’ from an old vocab section (who has those now?) would usually trigger a complete re-record.

With ElevenLabs, I can now produce new sections promptly, utilising its impressive array of voices across multiple languages. The authenticity and clarity of these voices are fantastic – I really can’t understate it – and it’s made maintaining the biggest language learning site for schools so much easier.

Supporting Individual Learning

As a language learner, ElevenLabs is more than worth its salt, too. It’s particularly good for assembling short listening passages – about a minute long – to practise ‘conversation islands’—a well-regarded polyglot technique for achieving conversational fluency.

Beyond language learning, the tool can be a great support to other academic projects. I’ve created concise narrations of complex topics, converting excerpts from scholarly papers into audio format. Listening to these clips in spare moments (or even in the background while washing up) has helped cement some key concepts, and prime my mind for conventional close study.

Flexible and Affordable Plans

ElevenLabs offers a range of pricing options to suit different needs:

Free Plan: Ideal for those starting out, this plan provides 10,000 characters per month, roughly equating to 10 minutes of audio.

Starter Plan: At £5 per month, you receive 30,000 characters (about 30 minutes of audio), along with features like voice cloning and commercial use rights.

Creator Plan: For £22 per month, this plan offers 100,000 characters (around 100 minutes of audio), plus professional voice cloning and higher-quality outputs.

For messing around, that free plan is not too stingy at all – you can really get a feel for the tool from it. Personally, I’ve not needed to move beyond the starter plan yet, which is pretty much a bargain at around a fiver a month.

Introducing ElevenReader

And there’s more! Complementing the TTS service, ElevenLabs has introduced ElevenReader, a free tool that narrates PDFs, ePubs, articles, and newsletters in realistic AI voices. Available on both iOS and Android platforms, the app doesn’t even consume credits from your ElevenLabs subscription plan.

Seriously, I can’t even believe this is still free – go and try it!

Final Thoughts

ElevenLabs has truly transformed the way I create and consume spoken content. It truly is my star tool from the current crop of AI-powered utilities.

The ElevenLabs free tier is enough for most casual users to have a dabble – go and try it today!

A robot playwright - now even more up-to-date with SearchGPT.

Topical Dialogues with SearchGPT

As if recent voice improvements weren’t enough of a treat, OpenAI has just introduced another killer feature to ChatGPT, one that can likewise beef up your custom language learning resources. SearchGPT enhances the LLM’s ability to access and incorporate bang up-to-date information from the web.

It’s a development that is particularly beneficial for language learners seeking to create study materials that reflect current events and colloquial language use. With few exceptions until now, LLMs like ChatGPT have had a ‘data cutoff’, thanks to mass text training having an end-point (albeit a relatively recent one). Some LLMs, like Microsoft’s Copilot, have introduced search capabilities, but their ability to retrieve truly current data could be hit and miss.

With SearchGPT, OpenAI appear to have cracked search accuracy a level to rival AI search tool Perplexity – right in the ChatGPT app. And it’s as simple as highlighting the little world icon that you might already have noticed under the prompt field.

The new SearchGPT icon in the ChatGPT prompt bar.

The new SearchGPT icon in the ChatGPT prompt bar.

Infusing Prompts with SearchGPT

Switching this on alongside tried-and-tested language learning prompt techniques yields some fun – and pedagogically useful – results. For instance, you can prompt ChatGPT to generate dialogues or reading passages based on the latest news from your target language country/ies. Take this example:

A language learning dialogue on current affairs in German, beefed up by OpenAI's SearchGPT

A language learning dialogue on current affairs in German, beefed up by OpenAI’s SearchGPT

SearchGPT enables content that mirrors real-life discussion with contemporary vocabulary and expressions (already something it was great at). But it also incorporates accurate, up-to-the-minute, and even cross-referenced information. That’s a big up for transparency.

Unsure where that info came from? Just click the in-text links!

Enhancing Speaking Practice with Authentic Contexts

Beyond reading, these AI-generated dialogues serve as excellent scripts for speaking practice. Learners can role-play conversations, solo or group-wise, to improve pronunciation, intonation, and conversational flow. This method bridges the gap between passive understanding and active usage, a crucial step in achieving fluency.

Incorporating SearchGPT into your language learning content creation toolbox reconnects your fluency journey with the real, evolving world. Have you used it yet? 

Greek text on a packet of crisps

Language Lessons from Packaging (And A Little Help from ChatGPT)

If you love scouring the multilingual packaging of household products from discounter stores (a niche hobby, I must admit, even for us linguists), then  there’s a fun way to automate it with LLMs like ChatGPT.

Take the back of this packet of crisps. To many, a useless piece of rubbish. To me (and some of you, I hope!), a treasure of language in use.

Greek text on a packet of crisps - food and household item packaging can be a great source of language in use.

Greek text on a packet of crisps

Normally, I’d idly read through these, looking up any unfamiliar words in a dictionary. But, using an LLM app with an image facility like ChatGPT, you can automate that process. What’s more, you can request all sorts of additional info like dictionary forms, related words, and so on.

From Packaging to Vocab List

Take a snap of your packaging, and try this prompt for starters:

Create a vocabulary list from the key content words on the packaging label. For each word, list:
– its dictionary form
– a new, original sentence illustrating the word in use
– common related words

The results should be an instantly useful vocab list with added content for learning:

Vocabulary list from food packaging by ChatGPT

Vocabulary list compiled by ChatGPT from a food packaging label

I added a note-taking stage to round it off. It always helps me to write down what I’m learning, adding a kinaesthetic element to the visual (and aural, if you’ve had ChatGPT speak its notes out loud). Excuse the scrawl… (As long as your notes are readable by you, they’re just fine!)

Handwritten vocabulary notes derives from crisp packet packaging

Notes on a crisp packet…

It’s a fun workflow that really underscores the fact that there are free language lessons all around us.

Especially in the humblest, and often least glamorous, of places.

ChatGPT takes conversation to the next level with Advanced Voice Mode

ChatGPT Advanced Voice Mode is Finally Here (For Most of Us!)

Finally – and it has taken SO much longer to get it this side of the Pond – Advanced Voice Mode has popped up in my ChatGPT. And it’s a bit of a mind-blower to say the least.

Multilingually speaking, it’s a huge step up for the platform. For a start, its non-English accents are hugely improved – no longer French or German with an American twang. Furthermore, user language detection seems more reliable, too. Open it up, initiate a conversation in your target language, and it’s ready to go without further fiddling.

But it’s the flexibility and emotiveness of those voices which is the real game-changer. There’s real humanity in those voices, now, reminiscent of Hume’s emotionally aware AI voices. As well as emotion, there’s variation in timbre and speed. What that means for learners is that it’s now possible to get it to mimic slow, deliberate speech when you ask that language learning staple “can you repeat that more slowly, please?”. It makes for a much more adaptive digital conversation partner.

Likewise – and rather incredibly – it’s possible to simulate a whole range of regional accents. I asked for Austrian German, and believe me, it is UNCANNILY good. Granted, it did occasionally verge on parody, but as a general impression, it’s shocking how close it gets. It’s a great way to prepare for speaking your target language with real people, who use real, regionally marked speech.

Advanced Voice Mode, together with its recently added ability to remember details from past conversations (previously achievable only via a hack), is turning ChatGPT into a much cannier language learning assistant. It was certainly worth the wait. And for linguaphiles, it’ll be fascinating to see how it continues to develop as an intelligent conversationalist from here.

Mapping out conversational probabilities - it's much easier with flowcharts.

Vocabulary Flowcharts : Preparing for Probabilities with ChatGPT

The challenge in preparing for a speaking task in the wild is that you’re dealing with multiple permutations. You ask your carefully prepared question, and you get any one of a number of likely responses back. That, in turn, informs your next question or reply, and another one-of-many comebacks follows.

It’s probability roulette.

What if you could map all of these conversational pathways out, though? Flowcharts have long been the logician’s tool of choice for visualising processes that involve forking choices. Combined with generative AI’s penchant for assembling real-world language, we have a recipe for much more dynamic language prep resources than a traditional vocab list.

And, thanks to a ready-made flowchart plugin for ChatGPT – courtesy of the charting folks at Whimsical.com – it’s really easy to knock one together.

Vocabulary Flowcharts in Minutes

In your ChatGPT account, you’ll need to locate the Whimsical GPT. Then, it’s just a case of detailing the conversational scenario you want to map out. Here’s an example for ‘opening a bank account in Germany’:

Create a flowchart detailing different conversational choices and paths in German for the scenario “Opening a bank account as a non-resident of Germany planning to work there for six months.” Include pathways for any problems that might occur in the process. Ensure all the text reflects formal, conversational German.

The result should be a fairly detailed ‘probability map’ of conversational turns:

A 'vocabulary flowchart' in German, created by the Whimsical.com GPT on ChatGPT.

A ‘vocabulary flowchart’ in German, created by the Whimsical.com GPT on ChatGPT.

Vocabulary flowcharts are another tool in your AI arsenal for speaking prep. Have you given them a whirl yet? Tell us about your own prep in the comments!

Lots of colourful neon shortcuts on a screen.

Apple Shortcuts for Smart Study Hacks

I’ve been optimising my iPad for study recently, trying to make it a portable, one-stop shop for reading and prep on-the-move. It’s no doubt another flex of my childhood awe for Inspector Gadget’s niece Penny, and her computer-in-a-book that could do everything.

Anyway, it’s led me to discover lots of features I half knew about, but had ignored for the duration of my Apple fanboydom. And one of the biggest revelations of rediscovery has been the Apple Shortcuts app.

In a nutshell, Shortcuts allows you to bundle all sorts of custom process chains into a single, iconisable action. For example, a shortcut could retrieve something, do something with the result, then present it in a certain way. People use them for all sorts of admin tasks – collecting stock prices and collating them in a spreadsheet with a single click, for instance.

The cool thing is that many third-party apps have extensions that you can link into shortcuts. ChatGPT, for example, which I find invaluable as a quick summary or explanatory tool, can be part of an action chain. And you can trigger chains not just with clicks, but from documents, via the share link.

Shortcuts for Smart Study : Brief Description

Using the app, I put together a quick shortcut I called “Brief Description”. It sends the current PDF (from a browser window, or from the Files app), to ChatGPT, prompting it for a one-paragraph summary.

A screenshot from Apple Shortcuts of a 'Brief Explanation' action using ChatGPT.

A screenshot from Apple Shortcuts of a ‘Brief Explanation’ action using ChatGPT.

As you can see, one of the best things about it is how you assemble a shortcut in more or less natural language, as you select items via an intuitive click-and-build interface. There are also plenty of resources for getting started and pushing the boundaries of it (like this very clued-up YouTube channel!).

The result of my shortcut offers a great way to get a paper summary, whatever the language:

Screenshot of an Apple Shortcuts link in the share menu.

Screenshot of an Apple Shortcuts link in the share menu.

When working through a bunch of resources, it’s great to ascertain in a click or two whether it might be a worthwhile full read, making this a brilliant time-saver. It’s even more powerful when combined with ChatGPT’s new(ish) memory features – my account ‘knows’ what I’ve been working on from recent chats, so is even better able to judge what’s useful.

For sure, I’ll be exploring more of this over the coming weeks, as it’s clear I’ve barely scratched the surface of how useful it could be yet. Have you used Apple Shortcuts to create smart study hacks? Let us know in the comments!

ElevenLabs Reader is the TTS robot you need!

ElevenLabs Reader : Enjoy it while it’s free!

I’ve raved before about the fantastic text-to-speech facility at ElevenLabs. Voices so realistic they pretty much pass for human, that work across languages, and can even clone your own.

Well, there’s a little-feted app that the ElevenLabs team are behind that is a similar show-stopper in its category. It’s simply called Reader, and is a free text-to-speech narration app for Android and iOS. 

Like the company’s web-based TTS service, it has the same range of emotive, expressive, ultra-realistic voices. It can also cope well narrating many languages, which are autodetected. Best of all for me is that it links with your device’s documents, so I can quickly import the papers I’m reading. Listening AND reading has made a massive difference to my comprehension and recall – multimodal is definitely the way forward for me!

You do get the odd strange artefact in the readout, but the product is still in Beta (likely the reason it’s currently completely free), and glitches are rare. What I’m also missing in it is the ability to tweak imported texts in-app, as you can do with Speechify. This would allow some cleaning of the file pre-narration (I lost count of the number of times I had to skip the page footer DOI link, which it hilariously mis-narrated many times). You can, of course, simply export and clean the files as text before importing, which gets round that.

In any case, they’re worth putting up with while the app is still free and in Beta. Even as it is, you have features here that you’d pay a small fortune for in other apps (ahem, Speechify). Definitely worth a punt if you’re looking for TTS support in your reading! Find download links for Android and iOS here.

Shelves of helpful robots - a bit like Poe, really!

Which LLM? Poe offers them all (and some!)

One of the most frequent questions when I’ve given AI training to language professionals is “which is your favourite platform?”. It’s a tricky one to answer, not least because we’re currently in the middle of the AI Wars – new, competing models are coming out all the time, and my personal choice of LLM changes with each new release.

That said, I’m a late and recent convert to Poe – an app that gives you them all in one place. The real clincher is the inclusion of brand new models, before they’re widely available elsewhere.

To illustrate just how handy it is, just a couple of weeks ago, Meta dropped Llama 3.1 – the first of their models to really challenge the frontrunners. However, unless you have a computer powerful enough to run it locally, or access to Meta AI (US-only right now), you’ll be waiting a while to try it.

Enter Poe. Within a couple of days, all flavours of Llama 3.1 were available. And the best thing? You can interact with most of them for nothing.

The Poe Currency

Poe works on a currency of Compute Points, which are used to pay for messages to the model. More powerful models guzzle through compute points at a higher rate, and models tend to become cheaper as they get older. Meta’s Llama-3.1-405B-T, for example, costs 335 points per message, while OpenAI’s ChatGPT-4o-Mini comes in at a bargain 15 points for each request.

Users of Poe’s free tier get a pretty generous 3000 Compute Points every day. That’s enough credit to work quite extensively on some of the older models without much limitation at all. But it’s also enough to get some really useful (8-ish-requests daily) use from Llama 3.1. And, thanks to that, I can tell you – Llama 3.1 is great at creating language learning resources!

Saying that, with the right prompt, most of the higher-end models are, these days. Claude-3.5-Sonnet is another favourite – check out my interactive worksheet experiments with it here. And yes, Claude-3.5-Sonnet is available on Poe, at a cost of 200 points per message (and that’s already dropped from its initial cost some weeks back!). Even the image generation model Flux has made its way onto the platform, just days after the hype. And it’s a lot better with text-in-image (handy if you’re creating illustrated language materials).

Poe pulls together all sorts of cloud providers in a marketplace-style setup to offer the latest bots, and it’s a model that works. The latest and greatest will always burn through your stash of Computer Points faster, but there’s still no easier way to be amongst the first to try a new LLM!

ChatGPT French travel poster

A Second Shot at Perfect Posters – ChatGPT’s Image Tweaker

The big ChatGPT news in recent weeks is about images, rather than words. The AI frontrunner has added a facility to selectively re-prompt for parts of an image, allowing us to tweak sections that don’t live up to prompt expectations.

In essence, this new facility gives us a second shot at saving otherwise perfect output from minor issues. And for language learning content, like posters and flashcards, the biggest ‘minor’ issue – the poor spellings that crop up in AI image generation – makes the difference between useful and useless material.

Rescuing ChatGPT Posters

Take this example. It’s a simple brief – a stylish, 1950s style travel poster for France. Here’s the prompt I used to generate it:

Create a vibrant, stylish 1950s style travel poster featuring Paris and the slogan “La France”.

I wanted the text “La France” at the top, but, as you can see, we’ve got a rogue M in there instead of an N.

ChatGPT generated image of a French travel poster

To target that, I tap the image in the ChatGPT app. It calls up the image in edit mode, where I can highlight the areas that need attention:

ChatGPT image editing window

Then, I press Next, and can re-prompt for that part of the image. I simply restate the slogan instructions:

The slogan should read “La France”.

The result – a correct spelling, this time!

ChatGPT French travel poster

It can take a few goes. Dodgy spelling hasn’t been fixed; we’ve just been given a way to try again without scrapping the entire image. Certain details also won’t be retained between versions, such as the font, in this example. Others may be added, like the highly stylised merging of the L and F in the slogan (a feature, rather than a bug, I think!).

But the overall result is good enough that our lovely 1950s style poster wasn’t a total write-off.

Another case of AI being highly imperfect on its own, but a great tool when enhanced by us human users. It still won’t replace us – just yet!

Image tweaking is currently only available in the ChatGPT app (iOS / Android).

Lots of owls - not quite the Duolingo one, but they're looking strict nonetheless!

Going Cold Owl (Once More, With Feeling)

Well, friends – I finally did it. I beat my Duolingo Leagues addiction.

Yes, it’s been months in the making. It was back in May last year that I wrote about that tipping point where Duolingo’s gamification switches from incentivising learning, to subverting it. After more than two years in Diamond, my main Duo activity had become all about chasing points, rather than finishing courses.

I’d even sussed out a ‘good’ trick – an easy lesson on Hindi alphabet characters – that I could mindlessly run through to amass points in my idle moments. Then I’d justify it with the two or three daily lessons I’d do that were relevant to my language goals.

Only it wasn’t good at all, in the grand scheme of things. What is was, was a great way to de-direct my learning time on what is otherwise a nice little supplementary app for my language plan.

Surely my idle moments were worthy of something more.

Letting Yourself Fall (and Trusting in a Soft Landing)

Gamified apps like Duolingo are adept at creating a sense of worth out of otherwise valueless tokens. A league title here, an achievement there – it feels good to notch these accolades up. But the real value of a language learning app is never the dressing, it’s the language-y filling in the centre. When it stops being about that, it’s time to stop.

So, in a final moment of take-the-plunge bravery, I stopped chasing the demotion cut-off last week. I let myself fall. And I won’t pretend I didn’t have several fleeting moments of panic when I thought – it’s not too late, I can still catch up!

But nope – I was resolute. And when, on Monday morning, I woke up to – gasp – Obsidian and not Diamond, do you know what? It felt liberating.

I’d broken the cycle.

didn’t feel like I’d left an exclusive club. I didn’t feel like I’d lost anything valuable. I just felt relieved.

Duolingo – Done Right (aka all things in moderation)

Since then, I’ve kept up my lengthy Duolingo streak. But not through mindless tap-tap-tap lessons – instead, through a couple of Swedish and Gaelic lessons to progress through the courses. Just as it should be.

If you’re in this autopilot pattern yourself, ask yourself: what do I gain? Reframing any kind of daily screen-addictive behaviour in this way is the first step in changing it.

Keen on more tips for breaking digital additions? Check out: