Generación de audio

Seed Audio 1.0

de ByteDance

ByteDance's all‑in‑one audio model.
Voice, music, and sound effects in one generation.

Seed Audio 1.0

Funciones clave

Escucha el rango

Documentary narrationSpeech

A warm, measured documentary voice-over.

0:00
0:12
Thriller voice-overSpeech

A hushed, tense line read, close and intimate.

0:00
0:12
Spice-market ambienceSound effects

A layered open-air market sound bed.

0:00
0:12
ThunderstormSound effects

A rolling storm building to a distant thunderclap.

0:00
0:12
Orchestral cueMusic

A short rising cue for strings and brass.

0:00
0:12
Lo-fi beatMusic

A relaxed beat with soft keys and vinyl crackle.

0:00
0:12

Especificaciones técnicas

ByteDance

Developed by ByteDance's Seed research team.

EN + ZH

English and Chinese, with broader support planned.

Up to 2 min

Two minutes per pass; extendable via continuation mode.

Up to 3

Up to three reference clips, each up to 30 seconds.

Casos de uso

One-pass video audio

Give a video clip its narration, sound design, and score in one generation, with no separate mixing step afterward.

Narrated explainers

A composed voice with light ambience and a music bed in one output. The model fills the sonic space around the narration.

Ads and promos

A spoken line, sound effects, and music as one ready-to-use track, made for short-form content.

Dialogue and audio drama

Multiple characters, each with a distinct voice and delivery, in one scene with matching ambience and timing.

Consistent series voice

Clone a character voice from a reference clip and carry it across a whole production without re-recording.

Audio editing and repair

Extend a take, fill a gap, swap a line, or stitch two recordings, without re-generating the whole track.

Ejemplos de prompts

Narrated explainer

Calm narrator, soft kitchen ambience: 'Combine the flour and butter.'

Edit prompt

Multi-speaker scene

Host: 'Why leave the city?' Guest: 'I needed quiet.' Quiet café ambience.

Edit prompt

Short ad

Upbeat voice: 'Your best run starts here.' Whoosh, brass sting, cheer.

Edit prompt

Audio drama

Detective, tense: 'Don't move.' Footsteps stop, a door creaks, a siren.

Edit prompt

Documentary voice-over

Measured narrator: 'The valley was unreachable.' Wind in pines, a hawk.

Edit prompt

Game moment

Deep narrator: 'The ancient seal has broken.' Stone grinding, dark hum.

Edit prompt

Precios simples

Comienza gratis hoy, con la opción de mejorar tu plan o cancelar cuando quieras.

Basic

$9/ mes
facturado como $0 por año

900 mensual créditos

1 usuario

Todos los modelos

Workflows

Standard

$24/ mes
facturado como $0 por año

3200 mensual créditos

1 usuario

Todos los modelos

Workflows

Pro

$45/ mes
facturado como $0 por año

6200 compartidos mensual créditos

1 usuario

+ hasta 4 más con costo adicional

Todos los modelos

Workflows

Pro Max

$170/ mes
facturado como $0 por año

24000 compartidos mensual créditos

1 usuario

+ hasta 9 más con costo adicional

Todos los modelos

Workflows

Enterprise

Para límites más altos

Personalizado

términos de precios y facturación

High-volume credits
Límites de asientos personalizados
Todos los modelos
Workflows
Pricing Gradient

Free

Para experimentar

$0

gratis para siempre

Hasta 20 créditos
Solo 1 usuario
Modelos limitados
Workflows
Comparar detalles de los planes

Preguntas frecuentes

What is Seed Audio 1.0?
Seed Audio 1.0 is ByteDance's all-in-one audio generation model. From one text prompt it produces voice, instrumental music, and sound effects together as a finished, mixed track. It also edits existing audio: extend a clip, fill a gap, swap a line, or stitch two takes.
How does voice cloning work in Seed Audio 1.0?
Seed Audio 1.0 clones a voice zero-shot from up to three reference clips of about 30 seconds each, with no training or fine-tuning. The cloned voice keeps its accent, tone, and character across the whole generation. You can also define a voice from a text description or a character image instead of a recording.
Can Seed Audio 1.0 generate multiple speakers at once?
Yes. Write a scene with several characters and label each line, for example Host: ... and Guest: ... . Seed Audio 1.0 gives each speaker a distinct voice, emotion, and pacing in a single generation.
How long can a Seed Audio 1.0 generation be?
Seed Audio 1.0 generates up to two minutes of audio in a single pass. Continuation mode extends it further while keeping the voice character and style consistent with what came before.
What languages does Seed Audio 1.0 support?
Seed Audio 1.0 supports English and Chinese, with broader language support planned. For voice cloning, matching the reference clip language to the output language gives the most consistent result.
How is Seed Audio 1.0 different from text-to-speech?
Text-to-speech turns text into a single voice track. Seed Audio 1.0 generates the whole scene, the voice, background music, and sound effects together in one output, and can revise specific sections afterward. The difference is scope: a finished audio production versus only the voice.

Otros modelos

MAI-Image-2.5

Microsoft

El modelo de imagen más avanzado de Microsoft. Texto más nítido en la imagen, ilustración estilizada y tomas de producto y empaque con calidad comercial.

Gemini Omni

Google DeepMind

El primer modelo de IA any-to-any de Google. Entra texto, imágenes, audio y video; sale un solo video.

Seedance 2.0

ByteDance

El buque insignia de video multimodal de ByteDance. Combina imágenes, clips, audio y texto en un solo prompt para producir video hiperrealista con sonido sincronizado.

Hailuo 2.3

MiniMax

El último modelo de video cinematográfico de MiniMax. Mayor calidad, movimiento más coherente y mejor comprensión del prompt que Hailuo-02.