> For the complete documentation index, see [llms.txt](https://docs.voicemoat.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.voicemoat.com/voice-and-audenai/voice-lab.md). # Voice Lab **In short:** Voice Lab is where you train your voice, see what audenAI read in your posts, and teach it how you like to write. It has two tabs, **Your voice** and **Teach audenAI**. It works per profile and is platform-aware (a Twitter profile and a LinkedIn profile each have their own Voice Lab). Open it from the sidebar. If a profile has not been trained yet, Voice Lab asks you to train it first. #### The two tabs | Tab | What it does | | ----------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Your voice** | What audenAI read in your posts, mostly as graphs: how you write, how far your posts reach, how they feel, and your habits. Every draft starts from this. | | **Teach audenAI** | Everything audenAI follows when it writes for you, in one place: your stories and views, your products, how you like it, and your rules. | Old links to Insights, Dimensions, Train audenAI, or Engage persona still work. They open the new tab that replaced them. #### Your voice
Voice Lab Your voice tab: How you write with Your usual post beside it, the Your posts dot graph by reach, and How your posts feel with the top feelings, humour, and usual strength

Your voice: how you write, your posts by reach, and how your posts feel.

Your voice has five cards. **How you write** is a short read of your content: a name for your style, one sentence about it, and the topics you post about most. Beside it, **Your usual post** shows how far your usual post reaches, and what share of your posts broke out, were typical, or fell flat. **Your posts** is a dot graph of your recent posts, each placed by how far it reached against your usual post: * **Broke out**: 2× your usual or more. * **Typical**. * **Fell flat**: half your usual or less. Click a dot to open the post panel. It shows the post and its numbers, a **Mark this post** menu, **Build from this** (opens the post in Studio), and a link to the post. **See all posts** opens the full list with its filters. **Mark this post** has two choices. **This is the voice** tells audenAI to lean on that post from your next draft. **Bad day** leaves it out of what audenAI learns from, including your stories and views. See Claim bank and learning from edits. **How your posts feel** shows your top 5 feelings by share, your humour, and your usual strength. audenAI picks a feeling from these first and keeps humour at your level. A note reminds you that audenAI never picks "Vulnerable, now" on its own. This card fills in once a training has labelled your posts; until then it asks you to re-train. See Feelings in your drafts. **Your habits** has six tiles: **How you open**, **Sentence length**, **Emoji**, **Format**, **Numbers and full stops**, and **Words you use**. audenAI copies these. **Details** on a tile opens what audenAI measured and its full read of that habit. **How you think** is how you make a point and what you come back to. It shows how you make a point (from your own experience, with a story, with numbers, step by step, and so on) by share, then how you build an idea, the metaphors and references you come back to, your humour, and how you come across. Examples and names show only if they really appear in your posts. audenAI writes the same way. The card fills in at your next re-train; until then it says so. #### Teach audenAI Teach audenAI is the steering wheel. You are not retyping your voice here. You are telling audenAI what to keep, what to mention, and what to avoid. It has four cards. **Your stories and views** is what you actually say, pulled from your own posts. It is one list, and each item is tagged **Story**, **View**, or **Avoid**. You keep, pin, edit, or remove (**Not me**) each one, and add your own. It shows 8 items first, then **Show more**. audenAI writes with it, and Studio's Stance check reads drafts against it. See Claim bank and learning from edits. **Your products** is what audenAI may mention for you. Turn on **Mention my products**, then choose where: **In replies** (**In comments** on LinkedIn) and **In posts**. Add up to 5 products, each with a name, one line on what it is, keywords for when to mention it, a Twitter handle (a LinkedIn Page or profile URL on LinkedIn), and a link. audenAI mentions a product only when a post or reply is really about its space. **How you like it** is five quick choices for every draft on that platform, saved with one **Save**: | Choice | Options | | ------------------------------------- | -------------------------------------------------- | | Emoji | Never, 1 or 2, 3 to 5, audenAI decides | | Capitals | Normal, all lowercase, EMPHASIS caps | | Replies (called Comments on LinkedIn) | A few words, One sentence, 2 or 3, audenAI decides | | Punctuation | Normal, No dashes, Minimal | | Lists | Like mine, •, -, → | Nothing changes until you press **Save**, and the choices apply to that platform only. Saving **EMPHASIS caps** also turns off the "No SHOUTING" check in Studio's Post Coach; moving away from it turns the check back on. A **From Intelligence** tag shows on a choice that a change from audenAI Intelligence set, until you change it yourself. **Your rules** is one list of plain sentences audenAI follows in every draft, wherever they came from: * words to never use, * rules tagged **You set**, **You said in chat**, or **From Intelligence**, * rules kept from your edits, tagged **From your edits**, * and **audenAI noticed** suggestions from your edits, with **Keep**, **Dismiss**, and **See the edits**. One box adds either a rule in plain words or a word to never use. The **Learn from my edits** switch pauses learning from your edits. Your rules and your products save as you go. {% hint style="info" %} The Post Coach check switches have moved out of Voice Lab. Each check now has its own switch in **Studio's Post Coach card**, under **Details**. See Studio. {% endhint %} #### Re-train The **Re-train** button sits at the top of Voice Lab, with its credit cost on it. A re-train reads your recent posts again and rebuilds your voice, including how your posts feel, your habits, and how you think. * **On Twitter**, the line under the button reads "Last trained ... · next re-train on ...". The button stays locked until that date. * **On LinkedIn**, the button shows its cost but has no date lock. It opens the training card again, so audenAI can read your posts through the Chrome extension or the posts you paste. * **On Free**, the button reads **Start trial** instead, when a trial is available. | | Free | Trial | Creator | Pro | Enterprise | | ------------------------------- | ------------- | ---------- | ---------- | ---------- | ---------- | | Re-train cost | not available | 20 credits | 20 credits | 30 credits | 50 credits | | Trainings per month | none | 4 | 2 | 4 | 8 | | Twitter re-train, at most every | not available | 7 days | 30 days | 15 days | 7 days | The first training is free. See Retraining your voice. {% hint style="info" %} A re-train also refreshes audenAI's full read (the longer read behind How you write and each habit's **Details**), within a limit: once every 30 days on Creator and the trial, twice every 30 days on Pro, and once every 7 days on Enterprise. Free plans do not get it. Everyday drafting does not need a refresh. {% endhint %} #### Per profile, per platform Voice Lab always reflects the **active profile**. Switch profiles and you are looking at that profile's voice. A Twitter voice and a LinkedIn voice are trained and stored separately, because you post differently in each place. Your How you like it choices and your rules are kept per platform too. #### Who can use it | | Free | Trial | Creator | Pro | Enterprise | | ------------------------------------------------------ | ------- | ----- | ------- | --- | ---------- | | Train a voice | no | yes | yes | yes | yes | | Your voice: How you write | yes | yes | yes | yes | yes | | Your voice: posts, feelings, habits, and how you think | blurred | yes | yes | yes | yes | | Teach audenAI | no | yes | yes | yes | yes | Free plans cannot train a voice. A Free account that already has one (for example, after a trial ends) keeps How you write and sees the rest blurred. #### Next steps * Training your voice: how training actually works on each platform. * The 10 signals: what audenAI listens for. * Feelings in your drafts: how audenAI picks a feeling for each post. * Claim bank and learning from edits: your stories and views, and how audenAI learns from your changes. * Retraining your voice: keeping it current as you evolve.