Pro free for everyone while Audio Estudio is in development · no card requiredSee what happens in 2027
Podcast studio · local-first

Give a voice to every
character in your script.

Create your project, assign TTS voices to your characters and generate the audio clip by clip. Your audio lives wherever you choose — in your browser or your own cloud. Never on our servers.

Get started See how it works
Try it here · Kokoro engineEnglish
0/150

● no card · your audio never touches our servers

scroll
★ The flagship · local voice

Clone voices on your own machine — no per-use cost.

Audio Estudio TTS is a desktop app that generates voice on your computer. No per-character billing, no API keys, and your audio never leaves your machine.

  • No per-use cost
    Generate all the audio you want.
  • Multilingual cloning
    Spanish and every language.
  • Several TTS models
    Pick the engine you like best.
  • Total privacy
    Your audio never leaves your machine.
Get started free Meet Audio Estudio TTS

● included in Pro · your audio never touches our servers

Audio Estudio TTS desktop app window
01

Create projects

Organize your scripts, episodes and drafts in a per-project workspace, with tabs.

02

A voice per character

Define your characters and assign them TTS voices from ElevenLabs, Gemini or a local model.

03

Generate clip by clip

Create, regenerate and tweak the audio line by line, without re-rendering everything.

04

Your audio, your cloud

Keep it local or sync it to your Drive, Dropbox or OneDrive. It never touches our servers.

01Workflow

Generate your podcast, clip by clip.

Each script line is an independent clip. Edit the text inline, generate the voice and regenerate only what changed — without re-rendering the whole episode.

Inline editingRegenerate per clipBatch queueDownload ZIP / master
AUDIO ESTUDIO
El Bosque de los Susurros
Mini Cosmos
Cocina con Abuela
LZ
Character
Todos
Estado
Todos
20 de 20 clips
01
N
Narrador
Había una vez, en lo más hondo del Bosque de los Susurros, una pequeña luciérnaga que había olvidado cómo brillar.
Generado
02
N
Narrador
Se llamaba Pípila, y aquella noche el cielo estaba más oscuro que nunca.
Generado
03
L
Lila
¡Pípila! ¿Dónde te has metido? Todos te están buscando.
Generado
04
B
Búho Filomeno
Una luciérnaga sin luz es como un libro sin palabras, pequeña Lila.
generando voz…
Generando
05
Z
Zorro Aurelio
¡Eh, eh! Yo conozco un atajo. Tres monedas de bellota y os llevo donde queráis.
Pendiente
06
H
Hada Musgo
La luz no se enciende por fuera, mi pequeña. Se enciende por dentro.
Pendiente
07
N
Narrador
Y entonces, muy despacio, su pequeño cuerpo comenzó a tibiarse.
error · rate limit 429 — reintentar
Error
Audio Estudio
conectado · es-ES · WAV 44.1 kHz
02Mixing

Voices, music and SFX on a multitrack timeline.

Place clips on the timeline, adjust timing with snap and mix narration, dialogue, music and effects. Export the master as WAV.

4 tracksSnap 0.1sMute / SoloComing soon
AUDIO ESTUDIO
El Bosque de los Susurros
Mini Cosmos
Cocina con Abuela
LZ
Editor de línea de tiempoEl Bosque de los Susurros · 4 pistas
Exportar WAV
0:14.80/0:36.00
SNAP0.1s
ZOOM 26px/s
Pistas
NarraciónNARRACIÓN
DiálogoDIÁLOGO
MúsicaMÚSICA
SFXSFX
0:00
0:02
0:04
0:06
0:08
0:10
0:12
0:14
0:16
0:18
0:20
0:22
0:24
0:26
0:28
0:30
0:32
0:34
0:36
Había una vez…
Pípila
¡Pípila!
Libro sin palabras
La luz por dentro
bosque-misterioso.wav
viento-hojas
ulular-búho
chispa-mágica
Audio Estudio
conectado · es-ES · WAV 44.1 kHz
03Voices

One character, one voice. You pick the engine.

Define your characters and assign each one a voice from Gemini, ElevenLabs or a local model. Switch provider without losing the assignment.

GeminiElevenLabsTTS Local

The local Kokoro model runs entirely in your browser — no API key, no cloud — and speaks natively in several languages.

Kokoro · localENEN-GBESFRHIITPT-BR
AUDIO ESTUDIO
El Bosque de los Susurros
Mini Cosmos
Cocina con Abuela
LZ
Ajustes del proyectoEl Bosque de los Susurros · voces e idioma
Voces de los personajes
Asigna una voz a cada character, de forma independiente por proveedor. Al generar, se usará la voz asignada aquí.
CharacterProveedorVozDescripción
N
Narrador
ElevenLabs
ElevenLabs
Adam
asignada
grave, cálido, narrador omnisciente
L
Lila
ElevenLabs
ElevenLabs
Rachel
asignada
niña, 9-12 años, curiosa
B
Búho Filomeno
Gemini
Gemini
Charon
asignada
anciano sabio, pausado
Z
Zorro Aurelio
TTS Local
TTS Local
kokoro · es
asignada
pícaro, socarrón
H
Hada Musgo
ElevenLabs
ElevenLabs
Bella
asignada
etérea, aguda, susurrante
Audio Estudio
conectado · es-ES · WAV 44.1 kHz
04Privacy

Your audio never touches our servers.

Start local in your browser. When you want it on any device, sync it to your own cloud — Google Drive, Dropbox or OneDrive. Our server only holds a pointer: the audio key and its file id. Never the bytes.

local-first by defaultyour own cloudpointers only
Where your audio livesPRIVATE
This browser
IndexedDB · local on this device
default
Google Drive
your account · synced
connected
Dropbox
connect your account
OneDrive
connect your account
Our server
pointer only · audioKey + fileId · metadata
no audio
Synced13 / 13 clips · your Google Drive
14:30:12INFOdrive · upload c13.wav ok · 89 kB → tu Google Drive
14:30:11INFOtts.elevenlabs · clip=c13 ok · 6.1s · 87 kB
14:30:04INFOstorage · indexeddb cache c13.wav (89344 bytes)
14:29:58INFOsync · servidor guarda solo puntero · sin bytes
Made with Audio Estudio

Two published channels, not a single microphone.

Script written with an LLM, characters with their own TTS voice and the mix put together in the studio. This is what comes out the other end — published and listenable today.

Spotify · podcastCover art of the Cuentos de Bolsillo podcast

Cuentos de Bolsillo

Children's stories narrated entirely with TTS voices: one character per role, a separate narrator and episodes assembled clip by clip.

narrator + charactersclip-by-clip mix
listen on Spotify
YouTube · channelThumbnail of the Audio Estudio intro video

@AudioEstudioPodcast

Tutorials with a script written by an LLM and voice-over generated in Audio Estudio, dubbed into several languages reusing the same script.

LLM scriptTTS voice-overmulti-language
see the channel
05PlansOpen beta · Pro free for everyone, 0 €

Start free. Upgrade to Pro when you need it.

These are the prices Audio Estudio will have once beta ends. Until then, the Pro plan is switched on for every account, at no cost.

Billing is disabled during the beta — nothing to choose yet

Free
0 €/ forever
Everything you need to put together your first real episode, with your own key.
Get started free
  • 2 projects
  • ~1500 words per project≈ 10 min of audio
  • 1 extra timeline track
  • 4 SFX / imported audio per project
  • All voice providers (BYOK)ElevenLabs · Gemini · Kokoro · Local
  • No cloud sync · single browser
  • Community support
Free during beta
Pro
0 €7,99 €/mo · 69,99 €/yruntil 2027
VAT included once billing starts
Switched on automatically on your account. No card required and no renewal to cancel.
Sign in and use it free
  • Unlimited projects
  • Unlimited words
  • Unlimited tracks
  • Unlimited SFX and imported audio
  • All voice providers (BYOK)
  • Cloud sync · multi-device
  • Priority support

● Secure payment with Stripe · cancel anytime · your key and your audio never touch our servers

What happens when the beta ends

Today → Dec 31, 2026
Pro free, no card
Every feature stays open. Nothing to sign up for, nothing to cancel.
Jan 1 → 31, 2027
Your 50% founder discount
If you created your account before 2027, your first annual year costs 35,00 € instead of 69,99 € (5,83 €/mo).
From Feb 2027
Free, without losing anything
If you don't take the offer, you move to Free. Nobody loses access to anything: everything opens, edits and exports. The only thing blocked is creating more and growing what you already have.
No project is ever deleted in the switch, not during the beta and not after it.

Give a voice to your next story.

Get started Sign in

● free to start · no card · local-first