How to prompt Seed Audio

The rules that matter most

1. 1

   Set the scene before the words

   Start with the place and its sound: a rainy platform, a roaring stadium, a quiet studio. Only the words in quotes are spoken; everything else is direction.

2. 2

   Describe each voice once, fully

   The first time someone speaks, give their gender, age, accent, timbre, emotion, and pace: Leo (a man in his forties, low and gravelly, tired, slow). After that, the name and a short delivery note are enough.

3. 3

   Write to the length you pick

   Choose the duration first. English speech runs about 2.5 words a second, so a short clip holds one short line. Too many words get cut off mid-word; too few leave silence at the end.

4. 4

   Write the prompt in the language of the lines

   A Spanish scene gets a Spanish prompt, from the description to the dialogue. Mixing an English prompt with lines in another language confuses the delivery.

5. 5

   Generate a few takes

   Every run is a new performance, even with the same seed. Run a line two or three times and keep the best.

Prompts to start from

• A narrator over ambience

  A quiet forest at dawn, birdsong slowly building, a stream running somewhere close. A narrator (a man in his sixties, standard British accent, warm and slightly gravelly, unhurried) says softly: "Every spring, the river remembers its way back to the sea." The birdsong continues to the end.

  Why it works: The scene comes first, the voice is a casting note, and the birdsong carries on so the clip ends on sound rather than on a cut. A 10-second duration fits it.

• Two voices, timed to the second

  A small radio studio late at night, the hum of equipment, rain against the window. Theo (a man in his late twenties, bright, quick, a little nervous) says: "[0.3s:3.2s] Okay, we're live. Say hi to everyone." June (a woman in her fifties, low, smoky, completely calm, slow) answers: "[3.8s:8.6s] Good evening, night owls. Pour something warm and stay a while." A soft jingle chimes; the rain continues to the end.

  Why it works: Each line opens with its own time window, sized to its words, with a short gap between the speakers and a quiet second at the end. Set the duration to 10 seconds.

• A music bed with no voice

  Generate pure background music and sound effects only. No voice, no dialogue, no narration, no lyrics.
  Style: warm, hopeful acoustic folk for a travel video. Create original music only.
  Background music: fingerpicked acoustic guitar, soft hand claps, a gentle upright piano, a light shaker.
  Sound effects: a car door closing, gravel under tires, wind on an open road. Keep effects clear but balanced under the music.
  Duration: about 30 seconds.
  Structure:
  [0:00-0:08] Guitar alone, light and curious; a car door closes.
  [0:08-0:20] Piano and shaker join, gravel under the tires, the tempo lifts.
  [0:20-0:27] The full band with hand claps, wind rushing past.
  [0:27-0:30] The music settles on one ringing guitar chord.
  Final mix: No vocals or spoken words. Bright and open, ready to sit under a travel montage.

  Why it works: Saying "no voice" at the start and again in the final mix keeps it instrumental, and the sections add up to the 30 seconds set in the settings.

• Sound effects, no music

  Inside a blacksmith's forge at night. The bellows wheeze and the coals roar up bright; a hammer rings on hot iron in a steady rhythm, three strikes and a pause, then the blade hisses as it plunges into a bucket of water and steam bursts up. Rain drums on the tin roof throughout. No music, no voices.

  Why it works: Every sound has a concrete source and a place in time, and the last line rules out what you do not want.

• A clean voice to save for a Character

  Clean, close-miked studio voice recording. No music, no background sound, no effects. Mara (a woman in her early thirties, standard American accent, low, warm, slightly husky, calm and assured) says at an even pace: "[0.2s:8.8s] I grew up on this coast. The tide always tells you something, if you are patient enough to listen."

  Why it works: One speaker, no background, and words from the first moment: the best kind of clip to save as a voice and give a Character. Set the duration to 10 seconds.

• A voice from a picture

  The old fisherman in the picture says warmly, a little amused, unhurried: "Well, look who finally showed up."

  Why it works: Upload a portrait as the Image and Seed Audio designs a voice to fit the face, so the prompt needs only the delivery and the words. A 5-second duration fits one short line.