← All models
ByteDance: Seed Audio 1.0NEW
bytedance-seed/seed-audio-1-0speech
ByteDance Seed's non-streaming audio generation: speech, tones and sound effects from a natural-language prompt; the voice can be set by a Seed speaker ID or a reference clip (cloning). Up to 120 seconds per request.
Price
Released
Sep 25, 2026
Parameters
inputrequiredHow to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
resp = client.audio.speech.create(
model="bytedance-seed/seed-audio-1-0",
input="Привет! Это Mixen AI.",
)
resp.stream_to_file("speech.mp3")
