What is Seed Audio 1.0 API?
Seed Audio 1.0 is ByteDance's non-streaming audio generation model for speech, sound effects, timbre control, and reference-guided audio creation. It's designed for workflows that need precise control over voice and audio characteristics without real-time streaming constraints.
Technical Specifications
- Supported inputs: Text prompt, optional reference audio
- Output: Generated audio (speech, sound effects, or custom-timbre voice)
- Editing: Reference-guided timbre and style control
- Endpoint: [уточнить у разработчика]
Performance Benchmarks
[embed]
Seed Audio 1.0 API Pricing
- Per second: $0.00325
Code Sample
[embed]
Comparison with Other Models
- vs other TTS models: Seed Audio adds sound-effect generation and reference-guided timbre control beyond standard text-to-speech.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Seed Audio 1.0 is documented as useful for narrative audio, scripted dialogue, short-form video, advertising, game content, podcast-style production, and other formats where sound carries the scene. It is also described as suitable for generating conversations with distinct speakers, including scripted podcasts, training scenarios, and character-driven storytelling.
It is documented for environmental ambience and action-matched sound effects alongside speech, which supports prototypes and short-form content. It is also described as useful for creating audio for advertising, including ad spots and other branded short-form pieces.
The model is documented as suitable for audiobook-style production, including narration, character voices, and sound design for a full book. It is also described as useful for video dubbing, with line timing aligned to the picture.
import requests r = requests.post( "https://api.aimlapi.com/v1/tts", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "bytedance/seed-audio-1-0", "text": "Hello from AI/ML API" }, ) print(r.json()["audio"]) # URL to the generated audio
const r = await fetch("https://api.aimlapi.com/v1/tts", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "bytedance/seed-audio-1-0", "text": "Hello from AI/ML API" }), }); const { audio } = await r.json(); console.log(audio); // URL to the generated audio
curl -X POST https://api.aimlapi.com/v1/tts \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"bytedance/seed-audio-1-0","text":"Hello from AI/ML API"}' # the JSON response contains "audio" — a URL to the generated speech
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Seed Audio 1.0 This page | Speech synthesis | |||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis |
Seed Audio 1.0 takes text as input and returns audio.
Seed Audio 1.0 became available on June 29, 2026.
Seed Audio 1.0 is priced at $0.00325 / sec.
Seed Audio 1.0 is billed per generation — a fixed charge per output rather than by prompt length.
Seed Audio 1.0 was built by ByteDance.
Send a request to https://api.aimlapi.com/v1/tts with bytedance/seed-audio-1-0 as the model id.
Yes. Seed Audio 1.0 is served through AI/ML API, so the same key and endpoint format used for other models applies.
No. Besides converting text to speech, it also generates sound effects, offers timbre control, and creates audio guided by a reference input.
No, it is a non-streaming model, meaning the full audio output is produced after processing rather than streamed as it's generated.
