Unicorn AI Studio platform for AI podcast generation, voice creation, and transcription

Create Your Audio Content

Turn your ideas into professional podcasts with AI voices. Write a script, choose your settings, and generate.

Project Voice & Style

Choose a project to apply its voice and pronunciations to new audio.

ScriptWrite a topic or full script for your podcast. Use multiple speakers by labeling them (e.g. Speaker 1, Speaker 2).

Tip: Type [pause:2] for a two-second pause, or [pause] for three seconds; pauses are added as silence and never read aloud. Add ♪ or (singing) only when you want a musical cue, like "Speaker 1: ♪ Happy birthday to you! ♪"

0 characters
ConfigurationChoose the model, number of speakers, voices, and delivery style for your podcast.

1

Balanced keeps a natural studio delivery with clear pacing for most podcasts.

Long-Form Speed

Fast is used for long Quickhorn scripts and stitches chunks after parallel generation.

Delivery Style
CFG 1.30 · Steps 5
1.3
5
0.9
0.9
Generation time depends on script length, model, and number of speakers.

Quick Voice NotesTurn speech into text as you talk. Good for quick notes, ideas, and messages.
Press and hold Space or the mic to transcribe
SpaceHold to record
Transcript
Your live transcript will appear here as you speak.

Call Recording

Capture, transcribe, and take notes during your calls with AI.

Take Meeting NotesCapture live transcription and AI-powered notes during your call.
Me Them
How it works Press Start Taking Notes — a live transcript appears below with Me and Them labels. On desktop, Whole call captures your mic and the call audio together without extra tools. In the browser, choose Share tab audio and enable audio sharing when prompted.

Review names, numbers, speaker labels, and action items against the recording before sharing.

Live NotesSee the conversation in real time with speaker labels and timestamps.
Notes will appear here as you speak...

Audio Library

All your generated, transcribed, and recorded audio in one place.

Name Duration Date Actions

Help & How To

Learn how to get the most out of Unicorn AI Studio. Follow quick start guides, find answers to common questions, and get support.

Quick Start GuidesGet up and running quickly with step-by-step instructions for each feature.

Podcast Generation

Turn your ideas into professional podcasts with AI.

  1. Enter a topic or write a script with Speaker 1, Speaker 2, and so on.
  2. Choose Quickhorn or a Silvermane model available on your plan.
  3. Select each speaker's voice and configure delivery.
  4. Click Generate Podcast and wait for the audio.
  5. Add ♪ or (singing) only for a musical cue.

Live Transcription

Get speech-to-text while you speak.

  1. Click the microphone or press and hold the space bar.
  2. Speak clearly into your microphone.
  3. Release to stop recording and see the transcript.
  4. Copy or clear the result with the provided buttons.

Call & Meeting Recording

Capture notes during a call or process a recording later.

  1. During a call, choose your audio source and start notes.
  2. In a browser, share tab audio when prompted to capture both sides.
  3. After a call, record or upload an audio file.
  4. Transcribe, review speaker labels, then download the transcript or summary.
Frequently Asked QuestionsFind answers to common questions about models, pricing, privacy, and more.
What's the difference between the TTS models?Compare Quickhorn, Silvermane Core, Studio, and Preview models.

Quickhorn is the fast single-speaker choice. Silvermane Core offers balanced quality and speed; Studio is the production choice; Studio Preview is experimental. Silvermane models require Pro and use more processing time.

Why is my podcast generation slow?Factors that affect generation time and tips to speed things up.

Longer scripts, more speakers, model choice, and a sleeping cloud model can extend generation time. Try Quickhorn for a quick draft, then use Studio for the final version.

How does pricing work?Plans, credits, and what's included.

Free includes 10 podcast minutes, 20 transcription minutes, and 5 scripts monthly. Starter includes 60, 120, and 50. Pro includes 300, 500, and 200 plus Silvermane models. The settings panel shows your current usage.

Where are my generated files stored?Find and manage your saved audio and transcripts.

Generated audio appears in the Library, where you can play, download, and delete it. Web files are linked to your account on the server. Desktop processing and storage depend on the selected local or cloud workflow.

How is my data processed? Is it private?Your device vs. Unicorn GPUs, and data handling.

In the desktop app, Use my device keeps generation and transcription on your computer, and Unicorn GPUs (paid plans) sends that work to Unicorn's secure processing. The web platform always uses Unicorn's processing. Free web content and feedback may be used to improve models; Starter and Pro content is not used for training. Extracted documents are discarded after text extraction.

TroubleshootingCommon issues and how to resolve them.

If capture fails, check microphone permission and the selected input. For browser call audio, choose Share tab audio and enable audio sharing in the browser prompt. If a voice or feature is unavailable, check your plan, or try again shortly if Unicorn GPUs are busy. Contact support if the issue continues.

Need More Help?Can't find what you're looking for? We're here to help.
Email UsGet in touch with our support team.info@coreledger.ca Visit Our WebsiteExplore more information and resources.www.unicornstudio.ca