Changelog

What's new?

We've made significant improvements to our audio generation. Your podcasts now sound even more natural and human-like.

What does this mean for you?

Your listeners will notice the difference. Conversations flow more naturally, pauses feel more authentic, and the overall listening experience is more engaging.

• More natural conversations: Improved pacing and intonation make dialogue feel real.
• Better listening experience: Your audience stays engaged longer with more human-sounding audio.

No changes needed on your end. Just create podcasts as usual and enjoy the improved quality.

— Stan

What's new?

You can now create a Podcast Series—a sequence of episodes automatically generated around a topic you choose, delivered on a schedule you set.

Want to learn about Ancient Rome in 12 weekly episodes? Or get a daily briefing on the latest in AI? Just set it up once, and let the episodes roll in.

How it works

1. Define Your Series: Choose any topic, from broad concepts like "The History of Jazz" to niche subjects like "Weekly Developments in Quantum Computing."
2. Set Your Schedule: Decide how many episodes you want per week and for how many weeks.
3. Listen Anywhere: Connect the series to your favorite podcast app via a unique RSS feed. New episodes will appear automatically, just like any other show you subscribe to.

Why it matters

Podcast Series transforms how you create and consume content. It's perfect for:

• Effortless Content Creation: Build an entire season of content without lifting a finger after the initial setup. Focus on the idea, not the weekly grind.
• Deep Dives & Learning: Create a personal, audio-first course on any subject. Master a new skill on your commute or during your workout.
• Building an Audience: Launch a consistent, long-running show that keeps listeners subscribed and engaged week after week.

This isn't just about generating single podcasts anymore. It's about creating your own automated, personalized radio station, tailored to your interests.

— Stan

What's new?

We've completely overhauled our script generation engine, and the results are in: scripts now generate 75% faster.

What does this mean for you?

Your time is valuable. This update means you can go from a blank page to a full podcast script in a fraction of the time. What used to take minutes now takes seconds.

• Faster iterations: Experiment with different topics and sources without the wait.
• Increased productivity: Spend more time refining your content and less time waiting for a draft.

We achieved this without sacrificing a single bit of quality. It's the same high-quality script generation, just delivered much, much faster.

No settings to change, nothing new to learn. Just enjoy the speed.

— Stan

What changed?

You can now update your podcast script by chatting with it. Type what you want changed in plain language, review the proposed edits, then accept or reject each one.

How it works

1. Open the chat in the editor (bottom panel or chat button)
2. Describe your change in natural words—no need to be formal or precise
3. Review suggestions that appear inline with your script
4. Accept or reject each edit individually before anything changes

Perfect for

• Tone shifts: "Make this sound more conversational" or "Add urgency to the intro"
• Content adjustments: "Simplify the technical explanation" or "Add a concrete example here"
• Pacing changes: "Speed up the opening" or "Give the conclusion more breathing room"
• Focus tweaks: "Emphasize the business impact over the technical details"
• Style refinements: "Remove metaphors" or "Make it more narrative"

Why it matters

Editing a script used to mean rewriting lines manually or regenerating everything from scratch. Now you can steer revisions conversationally while keeping full control. Each suggestion shows exactly what changes, and nothing updates until you approve it.

This closes the loop between "pretty good" and "exactly right."

Quick examples from the chat

Click any of these in the editor to see how it works:

• "Shift the tone to more inspirational storytelling while keeping the facts intact"
• "Simplify the explanation so a non-technical listener can follow along"
• "Add specific numbers or case studies to make it more concrete"
• "Dial back the metaphors and keep the language straightforward"

What you'll see

After you send a message, suggestions appear as cards next to the affected lines. Each card shows:

• What's changing: highlighted diffs for edits, removal notices for deletions
• Accept/Reject buttons: nothing happens until you decide
• Speaker changes: if a line moves between hosts, you'll see that too

Accept a suggestion and it updates immediately. Reject it and the script stays put.

Pro tips

• Be specific about audience or intent: "for beginners" or "to sound authoritative"
• Reference specific sections: "in the intro" or "when explaining the workflow"
• Mention what to avoid: "don't add jargon" or "keep it under 30 seconds"
• Iterate freely—refine multiple times to dial in the perfect version

— Stan

Hey! Prompts got an upgrade.

• Clearer intent = cleaner outlines
• Better tone matching and on-topic dialogue
• Fewer tangents and filler

No new switches—just write like you talk and we’ll do the rest.

— Stan

What changed?

You can now paste an existing two speaker script or transcript into the Prompt flow and import it directly as dialogue. We detect that it is a script, identify the speakers, and create lines instantly. No outlining or rewriting.

How it works

1. Choose Start from a prompt
2. Paste your dialogue
3. After content screening, the system detects scripts
4. Your lines appear in the editor, ready to edit or synthesize

If the text is not a direct script, we continue with normal generation from your prompt.

Why it matters

This is the fastest path when you already have a script. There is no paraphrasing. Your words become the episode, one line per turn. This improves accuracy, approval speed, and time to audio.

Perfect for

• Classroom dialogues, interviews, panel excerpts
• YouTube or webinar transcripts you want to voice
• Writer drafted scripts that should not be rephrased
• Quick imports from notes or previous episodes

Pro tips

• Keep speaker labels consistent. Names or letters both work. The importer assigns speakers based on the first time each one speaks
• Use ... where you want a natural beat
• If your text is not a strict back and forth, the system treats it as a prompt and generates a fresh script
• Title and description are not generated automatically in direct mode. Edit them yourself or use the normal generation flow if you want AI titles

Getting started

Create a new episode, choose Start from a prompt, paste your two speaker script, then select Create. Your dialogue appears immediately. Pick voices and generate audio.

— Stan

What changed?

You can now provide Additional instructions when creating a podcast from a website URL or a document (PDF). These notes guide planning and dialogue so the episode reflects your intent.

• Optional: leave it blank and everything works as before
• Precedence: if your instructions conflict with defaults, your instructions win
• Applied end‑to‑end: used in both the outline planning and the actual dialogue writing

How it works

1. Choose Start from a link or Start from a document
2. Paste a URL or upload a PDF
3. Fill in Additional instructions (optional) with any guidance you want
4. Pick style and duration, then create

Notes are incorporated during planning (sections/flow) and when drafting host dialogue.

> Starting from a prompt? No extra field—put your guidance directly in the prompt as usual.

Why it matters

This gives you precise creative control without extra steps. You can steer tone, focus, and audience expectations up front—reducing edits and getting to publish‑ready faster.

Perfect for

• Focus/angle: “Emphasize practical applications over history.”
• Audience: “Assume beginners; avoid jargon; expand acronyms.”
• Tone/style: “Conversational, upbeat, with concrete examples.”
• Pacing: “Tight sections, short intros, quicker transitions.”
• Do/Don’t: “Avoid brand names; include risks and trade‑offs.”

Pro tips

• Keep guidance concise and directive; bullets work well
• Specify who it’s for (beginners, execs, kids) and how it should feel (narrative, tutorial, debate)
• Call out must‑cover topics or things to avoid

Getting started

Nothing to enable—when you start from a URL or PDF, use the Additional instructions (optional) box right below the main input. Your notes will shape the outline and the dialogue.

— Stan

What changed?

You can now choose between two text to speech modes when producing audio: Good (default) and Best.

• Good: Fast, reliable, natural enough for long scripts at low cost.
• Best: Premium voice generation with richer prosody and emotional nuance.

Why it matters

Creators report common pain points:

• Moments that should feel emotional sounding flat
• Intros and ad reads needing more presence and warmth
• Tone drifting over long episodes
• Mixed language terms or brand names losing correct stress

Good handles these for most use cases. When you need that last bit of realism for high stakes audio, Best is available.

How it works

• Mode is set per episode in the editor.
• Use the Good/Best toggle in the editor header.
• Switching modes removes existing generated audio for that episode and requires regeneration, which uses credits.
• Voices reset to provider defaults after switching. Adjust voices as needed.

When to use each

Use Good for:

• Educational series, explainers, internal training
• Drafts, fast iterations, bulk catalog updates
• Episodes with limited emotional range

Use Best for:

• Trailers, ads, brand intros, launch announcements
• Narrative segments that require tension or empathy
• Final masters for public release

Pricing

• Good uses standard credits.
• Best uses 10x the credits. Choose it only where the extra realism is required.

Getting started

Open any episode, use the Good/Best toggle in the editor, then regenerate lines or select Generate all audio.

Stan

What is new

You can now create podcasts directly in your audience's language. Pick Spanish, Hindi, German, Japanese, Arabic, Swahili (and 60+ more) and the script is written natively in that language. No after‑the‑fact translation feel.

Why it matters

Listening in your own language lowers cognitive load. Complex ideas, technical walkthroughs or nuanced stories land faster and stick longer. This helps you:

• Make expert content accessible to teams in different regions.
• Reach new markets without rewriting everything manually.
• Let learners follow along without juggling a second tab for translation.
• Offer inclusive, language‑first onboarding or education series.

How cloning works

Language for an episode is fixed once created so timing, tone and future audio stay consistent. Need another language? Click Create language version. We duplicate the source inputs and generate a fresh script in the new language while the original stays untouched. Each version progresses independently (draft → refine → voice).

Use cases

• Publish an AI safety explainer simultaneously in English, Portuguese and Korean.
• Turn a long technical architecture brief into localized training series.
• Test demand in a new region with a single cloned episode before committing.
• Repurpose evergreen thought leadership into a multi‑language learning path.

Tell us which language or dialect you want polished voices and style presets for next.

{{EM}} Stan.

What changed?

You can now create podcasts from simple text prompts or ideas. Just describe what you want, and our AI will generate a complete podcast script with natural dialogue between two hosts.

How it works

1. Describe your idea: Enter a few sentences about what you want your podcast to cover
2. Choose your style: Pick from educational, conversational, narrative, or deep dive formats
3. Set duration: Specify how long you want the episode (1-60 minutes)
4. AI generates: Our system creates a full script with natural host dialogue
5. Customize & produce: Edit the script, choose voices, and generate audio

Perfect for

• Quick content creation from brief ideas or concepts
• Educational content explaining complex topics to specific audiences
• Thought leadership pieces on industry trends or insights
• Content repurposing from notes, outlines, or bullet points
• Brainstorming sessions turned into structured discussions

Example prompts

• "A 5-minute podcast explaining machine learning basics for beginners, using simple analogies"
• "Deep dive into the future of remote work, covering tools, culture, and productivity trends"
• "Conversational episode about sustainable investing for millennials, practical and actionable"

Why it matters

This dramatically lowers the barrier to podcast creation. No need for detailed outlines or scripts—just share your idea and let AI handle the structure, flow, and dialogue. Perfect for subject matter experts who want to share knowledge without spending hours on script development.

Pro tips

• Be specific about your target audience (e.g., "for beginners", "for executives")
• Mention the tone you want (professional, casual, energetic)
• Include key points you want covered
• Specify real-world applications or examples to include

— Stan

What changed?

The generator can now securely access the public internet while crafting your podcast script. That means:

• Coverage of breaking news and emerging stories.
• Inclusion of fresh stats, prices, rankings, and market data.
• Automatic link enrichment so sources are transparently cited.
• Smarter context disambiguation (the model double‑checks ambiguous facts).

How it works

For every generation, the system now automatically:

1. Builds focused search queries based on your topic.
2. Fetches and cleans candidate pages (paywall‑safe + robots aware).
3. Extracts structured nuggets (claims, figures, quotes, dates).
4. Runs a fact consistency pass to drop contradictions.
5. Injects a compact, attributed research digest into the model context.

Why it matters

This closes the gap between evergreen knowledge and what's happening right now. Perfect for market wrap‑ups, tech trend briefings, sports recaps, policy updates, or rapid commentary formats.

Safeguards

• Source diversity scoring prevents single‑site echoing.
• Automatic date validation flags stale articles.
• Hallucination guardrails compare claimed numbers to extracted originals.
• Applies only publicly accessible content and respects robots directives.

Getting started

Nothing to enable—live web research is on by default. Optionally provide focus keywords to steer retrieval and framing.

Let us know what real‑time formats you create—this unlocks a whole new style of timely audio.

— Stan