Marcus[like an evening news anchor, composed] Good evening. We begin tonight with breaking news from the port of Baltimore.
News
0:05
Turn any text into natural speech in seconds: paste it, pick one of 800+ voices and hear it read aloud. Free to start, no credit card.
Marcus[like an evening news anchor, composed] Good evening. We begin tonight with breaking news from the port of Baltimore.
0:05
Laura[intrigued] Okay, quick question before we start.
Laura Is a hot dog a sandwich?
0:35
Brooke[relaxed, like opening a favorite podcast] Hey everyone, welcome back to the show. Today I've got a story I just can't keep to myself.
0:06
Agatha[serene] Off the western coast of Scotland, the North Atlantic is waking
Agatha up.
0:51
Penelope[polite and clear, like a phone menu] Thank you for calling. For customer service, press one. To check the status of your order, press two.
0:08
Rupert[friendly] Welcome to the Valdeoncillo exhibition room!
Rupert You're about to set off on an extraordinary journey through time:
1:37
Ambrose[motivational] Every morning, forty million homes switch on the lights without
Ambrose a second thought.
0:44
Bernard[enigmatic] The storm had been circling Blackwood Manor for three days when
Bernard the letter finally arrived.
0:55
Andrés[como un presentador de informativos, sobrio] Buenas noches. Abrimos el informativo con una noticia que llega desde el puerto de Valencia.
0:06
Casandra[enigmatic] Prometió revolucionar la medicina con una sola gota de sangre.
Casandra Elizabeth Holmes, la joven que engañó a Silicon Valley, a los inversores y a sí misma.
1:05
Sara[relajada, como quien abre su pódcast favorito] ¡Hola, hola! Bienvenidos a un nuevo episodio. Hoy vengo con una historia que no me puedo callar.
0:06
Leonardo[intrigued] Son las seis de la mañana en Oaxaca, y la ciudad ya huele a chocolate
Leonardo y a tortillas recién hechas.
0:26
Nuria[amable y clara, como una centralita telefónica] Gracias por llamar. Para hablar con atención al cliente, pulse uno. Para conocer el estado de su pedido, pulse dos.
0:09
A text reader pronounces the words; Voyager 1 performs them. Write how it should sound —“hopeful, with a smile”, “nervous, like right before an exam”— and the same line takes on a new meaning.
32 emotions, plus any direction you write in your own words.
[hopeful, with a smile] Something new starts today. And I wanted you to hear it from me.
Same line, same voice. Only the direction changes.
YouTube, TikTok, Reels or tutorials: write the script and download a voiceover ready to edit.
Documents, articles or notes turned into audio, so you can listen anywhere.
Your newsletter or blog read aloud, in a voice people enjoy from start to finish.
Spoken versions of your writing for people with reading difficulties or low vision.
Greetings, menus and announcements in a clear, friendly voice, in every caller’s language.
The same voice in your app: a REST API and an MCP connector, up to 10,000 characters per call.
Text to speech APIEvery Voyager 1 voice has documented provenance: synthetic voices built from our own dataset, recorded by professional voice actors who were paid for it, and from public datasets licensed for commercial use.
Speech is generated on GPU servers in the EU, and projects and audio are stored in the EU.
Script, voices, effects and music on one timeline. Export the master.
Open the studioREST, up to 10,000 characters per request, watermark already in.
DocsClaude, Cursor or ChatGPT cast voices, direct, quote and generate.
Connect your agentThe same Voyager 1 on every plan. Cancel anytime.
See all plansYes, to get started: the Free plan gives you 10,000 characters a month with Voyager 1 and every voice, no credit card, for personal use. For commercial use, start with the Basic plan.
Yes. Voyager 1 shapes intonation and pauses the way a person does, and takes emotional direction in plain words: “cheerful”, “whispering”, “like a news anchor”.
55+ languages, with 800+ voices and accents from every region: American and British English, Castilian, Mexican and Argentine Spanish…
In the studio you write the text in blocks and download it as one mixed file; through the API, up to 10,000 characters per call.
Yes, from the Basic plan. The Free plan is for personal use only. It covers videos, ads, podcasts, training or your own product.
MP3 or WAV at 48 kHz, with voice, effects and music already mixed and mastered for where it will be heard.
Yes. Every file carries an inaudible watermark (AudioSeal) and Content Credentials (C2PA), so its origin can be verified. Designed in line with the EU AI Act.
AI text to speech in 55+ languages, with the emotion you ask for.