晓曼
A clear, gentle, professional, and friendly female voice suitable for podcasts, workplace training, and knowledge sharing.
ListenHub · Biblioteca de voces · 12 idiomas
ListenHub habla con 909 voces oficiales en 12 idiomas, y todas se pueden escuchar aquí mismo. Encuentra la que encaja y llévala directa a Texto a voz.
1–60 de 491 voces
A clear, gentle, professional, and friendly female voice suitable for podcasts, workplace training, and knowledge sharing.
A clear, bright voice at a moderately fast pace, suitable for science explainers, documentary narration, and other informative content.
A clear, bright female broadcaster with a moderately fast pace, full of energy and approachability, suitable for various professional explainers and podcast content.
A steady, magnetic voice at a moderate pace, suitable for various narrative content.
A crystal-clear, bright female voice at a fast pace, with a sweet, soft tone full of narrative depth and poetic quality, suitable for audiobooks, poetry recitation, and cultural programs.
A steady, resonant male voice with clear pronunciation, suitable for professional, serious knowledge sharing and content narration.
A clear, gentle male voice at a moderate pace, calm and steady, suitable for narration and storytelling.
A crystal-clear, sweet, and energetic young female voice at a moderately fast pace, suitable for animation dubbing, children's programs, and casual vlogs.
A clear, tender voice with a mellow, soothing tone at a moderately slow pace, suitable for audiobooks, meditation guides, and cultural program narration, delivering a serene and elegant listening experience.
A friendly, bright female voice that tells children's stories with a gentle, lively tone, full of infectious energy.
A clear, bright female voice at a moderate pace, suitable for friendly narration and knowledge sharing.
A mature, magnetic male voice with a steady pace, rich in narrative depth, suitable for history documentaries, audiobooks, and cultural programs.
A rich, full male voice at a moderately fast pace, full of magnetism and steadiness, suitable for historical narration, traditional storytelling, and audiobook narration.
A steady, tender, magnetic male voice at a slow pace, full of healing warmth, suitable for meditation and bedtime companionship.
A soft, warm voice at a slow pace, full of healing warmth, suitable for meditation and sleep aid.
A male voice with a fast, clear, and energetic delivery for live commerce, with an enthusiastic tone and strong persuasiveness.
A bright, clear voice at a fast pace, full of energy, suitable for live commerce, advertising, and other high-engagement scenarios.
A lively, playful childlike voice at a moderately fast pace, suitable for children's stories, animation, and game dubbing.
"佩奇猪" is an official ListenHub Mandarin Chinese female voice, suited to video dubbing, with a natural delivery.
A clear, gentle, and professional male voice, suitable for podcasts, explainers, and broadcasts.
A clear, friendly, confident, and steady male voice, suitable for various communication scenarios.
A steady, professional voice at a moderate pace with clear pronunciation and magnetic quality, suitable for business podcasts, news broadcasts, and knowledge sharing.
A clear, warm female voice at a moderate pace, calm and steady, suitable for narration and voiceover scenarios.
A steady, resonant voice rich in magnetism and narrative quality at a moderate pace, suitable for history explainers, audiobooks, and documentary narration.
"湾湾小何" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural delivery.
A gentle, soothing ASMR female voice at a slow pace with a soft tone, suitable for sleep aid, relaxation, and meditation, delivering a serene listening experience.
A soft, magnetic male voice at a slow pace, ideal for ASMR content to help listeners relax and fall asleep.
"沪普男" is an official ListenHub Mandarin Chinese male voice, suited to versatile audio creation, with a IP-inspired delivery.
"湾区大叔" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural delivery.
"妹坨洁儿" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural delivery.
An energetic, playful, and confident male voice, suitable for hero characters in animation or children's drama, such as Sun Wukong.
An endearing, good-natured male voice, suitable for characters in animation and children's stories.
"天才童声" is an official ListenHub Mandarin Chinese male voice, suited to video dubbing, with a natural delivery.
"樱桃丸子" is an official ListenHub Mandarin Chinese female voice, suited to video dubbing, with a natural delivery.
"呆萌川妹" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural delivery.
"浩宇小哥" is an official ListenHub Mandarin Chinese male voice, suited to general audio creation, with a natural delivery.
"广西远舟" is an official ListenHub Mandarin Chinese male voice, suited to general audio creation, with a natural delivery.
"豫州子轩" is an official ListenHub Mandarin Chinese male voice, suited to general audio creation, with a natural delivery.
A clear, soft female voice at a moderate pace, calm yet resolute, suitable for narration or inner monologue content.
"小何 2.0" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural and neutral delivery.
"小天 2.0" is an official ListenHub Mandarin Chinese male voice, suited to general audio creation, with a natural and neutral delivery.
"刘飞 2.0" is an official ListenHub Mandarin Chinese male voice, suited to general audio creation, with a natural and neutral delivery.
"云舟 2.0" is an official ListenHub Mandarin Chinese male voice, suited to general audio creation, with a natural and neutral delivery.
"魅力苏菲 2.0" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural and neutral delivery.
"甜美桃子 2.0" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural and neutral delivery.
"甜美小源 2.0" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural and neutral delivery.
"清新女声 2.0" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural and neutral delivery.
"撒娇学妹 2.0" is an official ListenHub Mandarin Chinese female voice, suited to versatile audio creation, with a character delivery.
"知性灿灿 2.0" is an official ListenHub Mandarin Chinese female voice, suited to versatile audio creation, with a character delivery.
"爽快思思 2.0" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural and neutral delivery.
"佩奇猪 2.0" is an official ListenHub Mandarin Chinese female voice, suited to video dubbing, with a natural delivery.
"少年梓辛/Brayan 2.0" is an official ListenHub Mandarin Chinese male voice, suited to general audio creation, with a natural and neutral delivery.
"邻家女孩 2.0" is an official ListenHub Mandarin Chinese female voice, suited to general audio creation, with a natural and neutral delivery.
"猴哥 2.0" is an official ListenHub Mandarin Chinese male voice, suited to video dubbing, with a natural delivery.
"大壹 2.0" is an official ListenHub Mandarin Chinese male voice, suited to video dubbing, with a natural delivery.
"暖阳女声 2.0" is an official ListenHub Mandarin Chinese female voice, suited to customer service, with a natural delivery.
Cada uno de los 12 idiomas tiene sus propias voces: el catálogo en español no es el inglés traducido, son voces distintas. Elige primero el idioma en el que vas a publicar.
Las etiquetas de escenario dicen para qué sirve una voz: podcast, audiolibro, documental, infantil. Las de estilo dicen cómo habla. Combina dos y unos cientos de voces se quedan en un puñado.
Todas las tarjetas reproducen la misma frase de demostración, así que comparas la voz en sí, no el texto que le ha tocado leer.
«Leer un texto» abre Texto a voz con esa voz ya seleccionada. Las voces de los tres idiomas originales conservan además sus accesos directos a Podcast IA y Voz IA.
Cada voz de esta página tiene un speaker ID, y ese ID es lo que usan las Skills de ListenHub, el servidor MCP, la CLI y la API para elegir voz. Copia uno desde una tarjeta, pégaselo a tu asistente y el audio que genere saldrá con esa voz.
Un solo comando dentro de tu proyecto. Claude Code, Cursor, Windsurf y OpenCode leen Agent Skills.
npx skills add marswaveai/skillsCrea una clave que empieza por lh_sk_. Tu asistente te la pedirá la primera vez que la necesite y la recordará después.
Crear una clave de APIPulsa «Copiar instrucción para agentes» en cualquier tarjeta de arriba. La frase llega con el nombre de la voz y su speaker ID ya puestos: añade lo que quieras que lea y envíala.
Usa la voz de ListenHub «晓曼» (speakerId: chat-girl-105-cn) para convertir esto en audio:Cualquier tarjeta te da la misma frase con su propia voz dentro.
Un episodio a dúo necesita dos voces que suenen a personas distintas, no a la misma persona dos veces. Escúchalas una junto a otra antes de decidir la pareja.
Un audiolibro o una lectura larga se juega todo en si la voz sigue siendo agradable a los cuarenta minutos. Aquí la constancia gana al efecto.
El material didáctico pide claridad antes que personalidad: esas voces viven bajo las etiquetas de documental y educación.
El doblaje de vídeo y los personajes piden registro, no neutralidad. Filtra por los estilos de personaje y varias emociones para encontrar voces que actúan.
No. Todas las demos de esta página se reproducen sin iniciar sesión. La cuenta solo entra en juego cuando quieres generar tu propio audio.
Hoy son 909 repartidas en 12 idiomas, cada idioma con su propio catálogo. La página cuenta lo que está publicado de verdad, no una cifra fija que se queda vieja.
Escuchar es gratis. Generar audio consume créditos de tu plan, y el coste depende del formato y la duración. Unas pocas voces están marcadas como Suscripción: puedes probarlas aquí, pero generar con ellas requiere un plan.
El escenario dice para qué sirve una voz: podcast, audiolibro, informativos, meditación. El estilo dice cómo habla: neutral, conversacional, personaje, varias emociones. Es el mismo vocabulario que usa el selector de voces dentro de la app, así que la voz que elijas aquí se comporta como esperas al llegar al editor.
Sí. Un podcast a dúo se escribe para dos presentadores y tú eliges ambos; justo por eso conviene escucharlos uno al lado del otro antes.
Sí, con la clonación de voz: con 25-35 segundos de audio limpio, tu voz se suma a tu propio selector. La clonación admite los mismos 12 idiomas que Texto a voz. Las voces clonadas son privadas de tu cuenta y nunca aparecen en esta biblioteca pública.
Cada perfil publicado lleva etiquetas de escenario o estilo y una descripción escrita. Usa las etiquetas para acotar la lista, lee la descripción para entender la intención y dale al play para juzgar la voz en sí.
Para cuando quieres que dos presentadores lo conversen entre ellos, en vez de una sola voz leyéndolo de principio a fin.
Cuando el guion ya está escrito y solo falta ponerle voz.
Cuando importa cómo se dice: varias voces en una sola pasada, o una frase que tiene que sonar con emoción de verdad.
Cuando ninguna voz de la biblioteca debería ser la que hable: graba 30 segundos y usa la tuya.
Todas las voces, ids y etiquetas en una sola descarga de texto plano, sin páginas que recorrer.
https://listenhub.ai/voices.txt