Turn text into professional narration using the 5 best audio models in the world. Generate, edit, and customize studio‑quality audio — all in natural language, right from Tess’s chat.
In practice, it’s like having a “voice talent cast” on demand to create voiceovers, training audios, podcasts, social media content, and much more.
How to use this feature in Tess’s chat
The Audio tool in Tess’s Chat lets you create professional narrations from text using 5 specialized models:
Orpheus Speech — 4 professional voices for corporate contexts
ElevenLabs Speech — All voices + ultra‑realistic custom IDs
OpenAI Speech — 6 premium voices with exceptional naturalness
Gemini Speech — 30 voices + the only one with dual narration in 24 languages
Voice Changer — Voice transformation while preserving emotions
Each model/voice has different characteristics (tone, intonation, naturalness, a more corporate or more relaxed “vibe”). This helps you choose the ideal voice for each context, like an institutional video, educational content, an ad, or a more “human” narration.
Practical applications (where narration shines)
voiceovers for videos (YouTube, Reels, TikTok, ads)
turn articles, scripts, and chapters into audio
create audio versions of written materials
narrations for classes, modules, and onboarding
audio for presentations, internal materials, product guides, and support scripts
Tips for narration with a professional result
Write as if it were “spoken”, use punctuation in your favor, after all, commas and periods control pauses and the rhythm of speech. Using dashes can be great for adding emphasis and, sometimes, lists with line breaks are clearer when you listen to them.
Besides that, you can write the acronym in full (e.g.: “Customer Success” instead of “CS”) when needed or give guidance in the text (e.g.: “Tess (pronounced ‘Tés’)”)
Make short versions and test. Before narrating a long script, generate 10–20 seconds to validate the chosen voice and clarity.
Voice Changer
Voice Changer can be used to turn one voice into another from an existing audio file. It’s great for:
characters and creative content
standardizing tone of voice across video series
“persona” tweaks for the brand
Credit usage
Narration and audio tools usually use more credits than a text chat, because they involve additional processing. If you want to optimize costs:
test in short snippets first
finish the script before generating the full version
keep a consistent voice/model to avoid rework
