ElevenLabs Flows API states vs Sume job status and webhooks
ElevenLabs Flows generations report pending, generating, completed and failed. Sume jobs use async, a 30-second wait cap and terminal-only webhook events.

The ElevenLabs Flows APIs are asynchronous: a generation reports pending, generating, completed or failed, and a request can include a webhook target. On Sume the equivalent is a job: submit with mode: "async", poll GET /v1/jobs/:id/status until it is terminal, or pass webhook_url and wait for a terminal event.
ElevenLabs details are from its August 17, 2026 changelog. Sume behavior is from Jobs and results and Webhooks, read 2026-10-01.
What does the Flows API add on the ElevenLabs side?
The entry says the new asynchronous APIs create, list and retrieve video, image and speech generations. It names the four states above and a webhook target for completion events. It also adds asset APIs so a generation can reference an uploaded asset or an earlier generation.
How do the states map to a Sume job?
Sume's docs call queued and processing normal non-terminal states and tell clients to poll until terminal: true. The table is a reading aid, not a one-to-one contract.
| Stage | ElevenLabs Flows | Sume job |
|---|---|---|
| Accepted, not started | pending | queued |
| Working | generating | processing |
| Done | completed | completed (result_ready: true) |
| Error | failed | failed with public error metadata |
Does a Sume sync request wait for the job?
Only up to a budget. The OpenAPI text says the wait is bounded by wait_timeout_seconds (max 30), and that bounds the HTTP request, not the job. When it runs out, poll status_url instead of resubmitting. For audio, /result returns 409 job_not_completed until result_ready is true.
What does a Sume webhook tell me?
Terminal events only: job.completed, job.failed and job.canceled. There are no progress or partial deliveries, so a generating-style intermediate state is something you poll for. Keep a polling fallback next to the webhook.
On cost: every Music Router model charges the fixed Music price per audio generation, per Music Router. A sibling post covers ElevenLabs Flows webhook targets.
Sources
Related posts
More in Developers
- is_final_audio_for_turn vs Sume TTS sentence boundaries: wav or mp3
ElevenLabs now emits is_final_audio_for_turn after every byte, even for MP3. Sume marks boundaries differently: sentence segments, sliced only for wav or raw.
- ElevenLabs Music Audio Reference vs Sume Music's image input
ElevenLabs Audio Reference guides Music v2/v2.5 with a track of about 30 seconds. Sume Music 1.0 takes a text prompt and one optional public HTTPS image URL.
- ElevenLabs Music v2.5 plan limits vs Sume's 5000-character prompt
ElevenLabs Music v2.5 plan chunks reach 6,132 characters, up to 30 lines of 200. Sume Music takes one 5000-character prompt and rejects duration fields.
- ElevenLabs STT 3 GB / 10 hour limit vs Sume STT 600 s jobs
ElevenLabs speech to text accepts files up to 3 GB and 10 hours in standard mode. Sume STT 1.0 reserves up to 10 minutes per job, so cut long recordings.
Written by Sume