Fireworks AI streaming ASR (deprecated)
Fireworks offered a WebSocket streaming transcription API (v1 and a v2 preview), but its changelog marks audio inference as deprecated on 2026-06-10 and the ASR docs page now returns not found.
Overview
Best for: Nothing new; listed so readers know it is gone.
At a glance
Deprecated: audio inference deprecated in the 2026-06-10 changelog. Historical price $0.0035/min ($0.21/hr).
n/a (deprecated)
n/a
n/a
n/a
n/a
n/a
Features
None listed.
Pricing
| What | Price | Unit |
|---|---|---|
| Historical streaming v2 | $0.0035 | per audio minute |
Do not plan on this service.
Free tier: n/a
Source: docs.fireworks.ai
Setup
- Do not start new integrations; migrate existing ones to another provider.
Endpoint
Formerly wss://audio-streaming.us-virginia-1.direct.fireworks.ai/v1/audio/transcriptions/streamingAuthentication
n/a
Warnings
Audio inference deprecated
Fireworks' changelog entry dated 2026-06-10 says audio inference and image generation are deprecated, and the querying-asr-models docs page is gone. Existing integrations should migrate.
Stale third-party listings
Model catalogs and comparison sites still list Fireworks streaming ASR prices; treat them as outdated.
Audio input to LLMs is different
Fireworks still supports audio as input to multimodal chat models (e.g. Qwen3 Omni), which is not a streaming ASR replacement.
Plus 12 warnings that apply to all speech-to-text, live APIs. See category warnings.
Limits
- Service deprecated.
Models and products
| Name | Status |
|---|---|
| streaming-speech (v1) | Deprecated |
| fireworks-asr-v2 / streaming v2 | Deprecated (was preview) |
Docs and sources
Docs
Sources used
- docs.fireworks.ai/updates/changelog.md
- fireworks.ai/blog/audio-september-release
- fireworks.ai/blog/streaming-audio-launch
Exact shutdown date for existing customers.