One public contract
Integrate one versioned endpoint and one response format instead of maintaining separate audio-generation clients.
◇ Seed Audio 2.0 APISeed Audio 2.0
Seed Audio 2.0
API for production
audio generation
Generate dialogue, ambience, music, foley, and sound effects from one prompt. Build complete sound scenes through a stable asynchronous task interface with predictable credit settlement.
API access is available after a plan or credit purchase.POST /v2/audio/generations202 Accepted
curl -X POST https://api.seedaudio.co/v2/audio/generations \
-H "Authorization: Bearer $SEED_AUDIO_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: request-001" \
-d '{
"model": "seed-audio-2.0",
"prompt": "A midnight radio drama with soft rain",
"format": "mp3",
"duration_seconds": 30
}'MODELseed-audio-2.0
MODEAsynchronous
BILLING5 credits/min
MINIMUM5 credits
FORMATSMP3 · WAV · PCM · OGG
PROMPT LIMIT2,048 chars
PRODUCTION READY
One Seed Audio 2.0 API, fewer integration problems.
Keep one public contract while generation orchestration, compatible fallback, managed output storage, and credit settlement happen behind the scenes.
Asynchronous by design
Submit work immediately, poll a durable task status, and retrieve the result only when every audio layer is ready.
Predictable credit billing
Reserve credits at submission, settle against actual output duration, and automatically return unused balance.
SEED AUDIO 2.0 API CAPABILITIES
Control the audio scene, references, and output.
Expose the controls your product needs without leaking provider-specific fields into your application.
Prompt-driven sound scenes
Describe speakers, emotion, timing, ambience, background music, and sound events in prompts up to 2,048 characters.
Audio or image references
Guide a task with up to three audio references or one scene image. Map every reference clearly inside the prompt.
Voice and delivery controls
Tune voice direction, language, speed, volume, pitch, sample rate, and output format when your workflow needs them.
Production-friendly output
Request MP3, WAV, PCM, or OGG. Successful tasks return a stored audio URL, duration, format, and final credit usage.
Queryable task status
Create a task with POST, then poll its ID with GET until it becomes succeeded, failed, or canceled.
Safe request retries
Send an Idempotency-Key so a repeated submission returns the original task instead of generating and charging twice.
BUILT WITH SEED AUDIO 2.0
What teams build with the Seed Audio 2.0 API.
Use the same asynchronous workflow for a single asset, a creator tool, or a larger audio-generation pipeline.
Video and short-film sound
Generate dialogue, room tone, transitions, background music direction, and foley concepts for video scenes and prototypes.
Podcasts and audio drama
Create narrated scenes, multi-character story moments, mood beds, and episodic audio drafts from structured prompts.
Games and interactive content
Produce environmental ambience, character moments, UI sounds, and event-driven audio variations for rapid iteration.
BGM and creative direction
Turn mood, pacing, instrumentation, and narrative function into background music drafts for a wider workflow.
Sound effects and foley
Describe physical actions, materials, distance, space, and timing to generate sound-effect and foley-style results.
Batch content pipelines
Use task IDs and idempotent creation to coordinate many independent audio jobs from your queue or application backend.
ASYNCHRONOUS WORKFLOW
From API key to audio URL.
Seed Audio 2.0 is asynchronous by design, so long-running sound-scene generations never need to keep a request connection open.
◇ Create an API key
Sign up, purchase credits, and create a secure key from your account settings.
≋ Submit a generation
Send a prompt and optional audio or image references to the Seed Audio 2.0 generation endpoint.
◷ Poll for the result
Query the task ID every few seconds until the output URL and final credit usage are available.
SEED AUDIO 2.0 API PRICING
Pay for actual generated duration.
API tasks use the same credit wallet as the web product. Final usage is calculated at 5 credits per generated minute, rounded up to a whole credit, with a 5-credit minimum.
- Credits are reserved before a task begins, preventing concurrent requests from overspending the wallet.
- After success, unused reserved credits are returned automatically.
- Failed tasks return the full reservation and do not create an extra charge.
Example final charges
Up to 60s5 credits
Up to 120s10 credits
Up to 10 min50 credits
Up to 60 min300 credits
A strong fit for asynchronous generation.
Choose Seed Audio 2.0 when your product can create a job and wait for a generated asset instead of maintaining a live audio connection.
- Backend services, creator tools, and queued workflows
- Scenes combining speech, ambience, music, and effects
- Applications needing durable result URLs and usage records
Design around the API contract.
The current version focuses on reliable task creation and polling. Clear boundaries make the first integration smoother.
- Asynchronous generation, not real-time streaming speech
- Poll task status until completion
- API access requires a paid plan or credit purchase
FAQs
Seed Audio 2.0 API questions.
Practical answers for evaluating and integrating the API.
What is the Seed Audio 2.0 API?＋
It is an asynchronous generation interface for creating complete audio scenes from prompts and optional references, including dialogue, ambience, music, and sound effects.
How do I call the Seed Audio 2.0 API?＋
Create an API key, submit a POST request to the generation endpoint, retain the returned task ID, and poll that task until a durable audio URL is ready.
How is API usage charged?＋
Generation uses 5 credits per generated minute with a 5-credit minimum. Reserved but unused credits are returned after the task settles.
Can I send reference audio or an image?＋
Yes. A generation may use up to three short audio references or one image reference. Map every reference explicitly in the prompt.
Do I need to integrate audio providers separately?＋
No. Your application integrates one versioned Seed Audio 2.0 contract while compatible provider orchestration remains behind the interface.
Does the API support real-time streaming or webhooks?＋
The current API is designed for asynchronous tasks and polling. It does not provide real-time streaming speech or public webhooks yet.
Which output formats are available?＋
You can request MP3, WAV, PCM, or OGG output, depending on the requirements of your production pipeline.
START BUILDING
Ready to add AI audio to your product?
Create an account, purchase credits, and make your first Seed Audio 2.0 API request in minutes.