Text to speech · Korean, Japanese, Chinese, English
Generatore vocale AI: dal testo alla voce in 4 lingue
Pickshot's AI voice generator reads your text aloud. Paste a script, pick its language and a voice, and download the speech. Viola, a Pickshot-series voice model, has nine voices that each speak Korean, Japanese, Chinese and English; Cello and Harp each have one built-in voice; partner voice models add dozens of preset voices at their credit price. The price is shown before you run, and during a membership the Pickshot-series voices need no credits.
Nessuna installazione. Nessuna carta di credito. Privato per impostazione predefinita.
AI voice generator at a glance
- Prezzo
- Credits per 1,000 characters, shown before you run; none for the Pickshot-series voices during a membership.
- Voci
- Viola has nine voices (Hana, Mio, Lian, Sora, Baek, Joon, Eli, Ren, Noah), each speaking Korean, Japanese, Chinese and English; Cello and Harp have one built-in voice each.
- Lunghezza
- Viola and Harp read up to 1,200 characters at a time, Cello up to 1,000; partner models take longer texts.
- Velocità
- 0.5× to 2× on the models that offer it.
- Also here
- Music from Sonata, Nocturne and MiniMax-Music3, and sound effects from Etude, in the same studio.
- Account
- A free account is needed to make anything; signing up asks for no card.
- Lingue
- Pages, studio and prompts in English, Korean, Japanese and Simplified Chinese
- Watermark
- No visible watermark; each file carries metadata that marks it as AI-generated.
Aggiornato
What is an AI voice generator?
An AI voice generator, or text-to-speech (TTS) model, turns written words into spoken audio in a chosen voice and language. Pickshot's audio studio makes speech, music and sound effects in one place, and its song maker turns lyrics into a sung song. Each Viola, Cello and Harp voice has a play button with a sample, and the audio samples page lets you hear the models by language and situation before you make anything.
Why make voices with Pickshot
Nine voices, four languages
Viola's nine voices (Hana, Mio, Lian, Sora, Baek, Joon, Eli, Ren and Noah) each read Korean, Japanese, Chinese and English, and each sounds most natural in its own language; two of them read Chinese with a regional accent.
A voice for each kind of script
Cello reads all four languages in one built-in voice, with samples for news, ads, explainers and audiobooks. Harp's built-in voice is strongest in Korean and English and also reads Japanese and Chinese.
No credits during a membership
During a Plus, Pro or Max membership, Viola, Cello and Harp need no credits. Without one, speech is priced per 1,000 characters and the price is shown before you run.
Language and speed
Choose the language your text is written in, then a voice for it. On the models that offer it, a slider sets the speed from 0.5× to 2×.
Music and sound effects too
Switch to Music for an instrumental or a song with lyrics from Sonata, Nocturne or MiniMax-Music3, or to Sound effects for rain, footsteps or a closing door from Etude. For a full song with lyrics and a cover picture, the song maker walks you through it.
Hear it before you make it
Press play next to a Viola, Cello or Harp voice to hear a sample. The audio samples page collects speech, music, song and sound-effect samples in four languages, each with a button that opens the studio with the same text.
How to make an AI voice-over
Apri lo studio audio
Choose Text to speech and a model. The Pickshot-series models Viola, Cello and Harp come first; partner voice models follow.
Paste your script and pick a voice
Type or paste the text, choose its language, pick a voice (press play to hear it) and set the speed where the model offers it. The counter under the text shows how many characters the model takes.
Make it and download
Check the price on the button, press it, and download the audio from My creations once it is done.
Typical text-to-speech tools vs. Pickshot
Many TTS tools are built around one main language and leave music and sound effects to other apps. Pickshot puts voices, music and sound effects in one studio for Korean, Japanese, Chinese and English.
Strumenti tradizionali
- − Voices built for one main language
- − Music and sound effects in other tools
- − Voice samples scattered across pages
- − Screens and help mostly in English
Pickshot
- ✓ Viola's nine voices each read Korean, Japanese, Chinese and English
- ✓ Speech, music and sound effects in one audio studio
- ✓ A play button on each Pickshot-series voice and a samples page in four languages
- ✓ Screens, help and errors in four languages
Casi d'uso
/01
Voice-overs for short videos
Turn a script into narration for Shorts, Reels, a slideshow or a product clip.
/02
Lessons and explainers
Read course notes, guides or help pages aloud in Korean, Japanese, Chinese or English.
/03
Stories and audiobooks
Give a children's story or a web-novel chapter a narrator; Cello's samples include audiobook-style reading.
/04
Character lines
Try lines for a game, a webtoon trailer or an AI influencer in different voices before choosing one.
/05
Announcements and ads
Read a shop announcement or an ad script in each language you sell in.
Acquista crediti quando ne hai bisogno; gli abbonamenti funzionano con crediti
I nuovi account ricevono 50 crediti. Gli account gratuiti possono generare immagini illimitate sul sito web con i 5 modelli base, senza consumare crediti. I video Lacquer sono gratuiti sul sito: 3 al giorno, fino a 5 secondi per clip. Gli abbonati usano i modelli inclusi senza limiti né addebiti di crediti. Altri modelli e API/MCP sono a pagamento separato.
Pickshot-series models without credits · 4 generations at a time · Unlimited free-model images (Higher priority than Free)
Pickshot-series models without credits · 8 generations at a time · Unlimited free-model images (Higher priority than Plus)
I Booster Pass e gli abbonamenti sono temporaneamente esauriti. I crediti e gli abbonamenti che hai già restano validi fino alla scadenza.
Domande
Is the AI voice generator free?
Signing up is free, and every generation needs an account. Speech is priced per 1,000 characters and the price is shown before you run; during a Plus, Pro or Max membership the Pickshot-series voices need no credits.
Which languages and voices are there?
Korean, Japanese, Chinese and English. Viola has nine voices that speak all four, each most natural in its own language; Cello and Harp each have one built-in voice, and Harp is strongest in Korean and English. Partner voice models bring their own preset voices, between four and thirty per language.
How long can the text be?
Viola and Harp read up to 1,200 characters at a time and Cello up to 1,000. Partner models take longer texts, and the counter under the text box shows the limit of the model you picked.
Can it make music and sound effects?
Yes. In the same studio, Music makes instrumentals or songs with lyrics (Sonata and Nocturne from 30 seconds to 5 minutes, MiniMax-Music3 full sung songs of up to 5 minutes), and Sound effects makes short sounds with Etude. The song maker helps you write lyrics and adds a cover picture.
Can I use the audio commercially?
You own the audio you make, and Pickshot's Terms do not forbid commercial use, but each model's licence also applies, as listed on the licences page. Do not use it to impersonate real people, and label AI audio wherever a platform asks for it.
Can I hear the voices first?
Yes. Each Viola, Cello and Harp voice has a play button in the studio, and the audio samples page has speech samples by model, language and situation, each with a button that opens the studio with the same text.
Does it work on a phone?
Yes. The audio studio, the voice samples and the players work in mobile browsers.
Give your script a voice
Sign up free, paste a few lines and hear them in Korean, Japanese, Chinese or English; the price is shown before you run.
Inizia a creare gratis