Seedream 5.0 Flash turns a written description, with up to 14 reference pictures if you have them, into one image in HD or 2K, in shapes from tall 9:21 to wide 21:9. It is the quick version of Seedream 5.0, made for interactive use and for runs of many images. Pick it while you refine a look or fill a catalogue.
Seed Audio 1.0
by Bytedance SeedReleased 25 September 2026
Seed Audio 1.0 takes a written description of the voice, the tone and the sound you want, and gives back a finished audio file in one go rather than a live feed. Speech and other audio come from the same description, so you describe the delivery in words instead of picking from a voice list. Use it when the voice and mood are part of the brief. For plain narration in a preset voice, Orpheus 3B or Aura-2 fits better.
Where your request runs
One company runs this model. OpenDunes sends every request to it.
You pay the price of the provider that served your request. Prices read 02:48 · speed over the last 30 minutes · uptime over 3 days.
What it costs
You pay for what each request uses. No subscription, no minimum.
One paragraph read aloud, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Second of audio | 0,83 DA |
per second of audio returned
Everyday jobs, priced
- When you pay
- After the answer, from your balance. Nothing is held.
- Why it varies
- The length of the audio made.
- After each one
- The exact charge shows on the request.
Call it in code
Swap the base URL and the key. Your OpenAI code runs unchanged.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://opendunes.com/v1",
api_key=os.environ["OPENDUNES_API_KEY"],
)
with client.audio.speech.with_streaming_response.create(
model="bytedance-seed/seed-audio-1-0",
input="مرحبا بكم في متجرنا. التوصيل مجاني في وهران.",
voice="alloy",
) as resp:
resp.stream_to_file("speech.mp3")Runs this request once on your balance.
Limits
The hard numbers — what it can take in, what it can give back, and where it stops.
- Context window
- not stated
- Max output
- not stated
- Reads at once
- not stated
- Longest reply
- not stated
- Tokenizer
- Other
- Released
- 25 Sep 2026
Questions about Seed Audio 1.0
How much does Seed Audio 1.0 cost in dinars?
About 33,28 DA per paragraph read aloud. ↓ 49,80 DA per minute of audio.
Is Seed Audio 1.0 free? Can I try it?
No. You pay per use from your balance in dinars, with no subscription. The chat has free models for free messages every day.
What is Seed Audio 1.0 best for?
Seed Audio 1.0 takes a written description of the voice, the tone and the sound you want, and gives back a finished audio file in one go rather than a live feed. Speech and other audio come from the same description, so you describe the delivery in words instead of picking from a voice list. Use it when the voice and mood are part of the brief. For plain narration in a preset voice, Orpheus 3B or Aura-2 fits better.
How do I pay for Seed Audio 1.0 without an international card?
Add credit in dinars with your Edahabia or CIB card. Every model, Seed Audio 1.0 included, is paid from that balance. No foreign card, no conversion.
Does Seed Audio 1.0 work in Arabic, French or Darja?
Bytedance Seed names no languages for Seed Audio 1.0. Arabic, French and Darja: not stated.
How many voices, and can it clone mine?
Voices: not stated. Cloning from a sample: yes.
Who makes Seed Audio 1.0, and when was it released?
Bytedance Seed. Released 25 September 2026.
Other Bytedance Seed models, priced in dinars
See all Bytedance Seed modelsSeedream 4.5 takes a written description and up to 14 reference pictures and draws up to ten images per request, in HD, 2K or 4K. Its strength is editing consistency: when you change a picture it keeps the subject's details, so a product or a face stays the same across variations. Pick it for batches of variants on one subject.
Seedream 5.0 Pro creates and edits images: send a written description and up to 14 reference pictures, and get one image in HD or 2K. It is the version for commercial visual work where an edit has to change exactly what you asked and leave the rest alone, and where scenes must look lifelike.
You send written words and up to ten reference pictures, and it sends back one picture, which can be a tall 9:16 frame for a phone screen. Its best work is the brief a designer hands over, such as a product shot built from a sketch and a colour list, then adjusted until it looks right. It can return the same picture twice from the same request, so a set of matching visuals stays matched across a campaign. It stops at 4K, offers no see-through background and gives one picture per request, so large print or a logo cut-out needs another kind of tool.