Skip to content
AnyRouter

Eleven Flash v2.5Disabled since Jul 26, 2026

The catalogue was narrowed to models whose output is text or embeddings; this model's output is audio (text-to-speech), so it was taken out of service. Related: #1551 (these SKUs bill $0 on a metered backend).

Also accepted:eleven-flash-v2-5
Elevenlabs
Compare

ElevenLabs' low-latency Flash v2.5 text-to-speech model, available as a partner-hosted SKU on Cloudflare Workers AI. Tuned for fast multilingual speech generation from text.

Providers
Capabilities
cloudflare
cloudflare
$0.05 per 1K characters of input text—
Usage analytics

Loading usage…

API & code

Speech API

/api/v1/audio/speech

Text-to-speech audio generation.

Uptime & Health
No uptime data yet

These providers haven't been health-probed for this model yet. The router still routes around upstreams that fail live requests — uptime fills in once probe history accrues.

Share cards
Eleven Flash v2.5 share card
Eleven Flash v2.5
cloudflare upstream share card
cloudflare upstream
Credits
Speech output
Voice — voice_id

ElevenLabs voice ids are opaque per-account strings (e.g. "21m00Tcm4TlvDq8ikWAM"). Copy one from the ElevenLabs Voice Library — there is no default, and a request without one is rejected.

Output formats — response_format
mp3opus
Languages

Multilingual. Pass `language_code` (ISO 639-1) to pin a language.

Price

$0.05 per 1K characters of input text

ArchitectureTransformer
Categoryaudio
ReleasedJul 24, 2026
Modalities
→
Capabilities
Speech models return raw audio bytes, not JSON — write the response body to a file. They cannot be called through chat completions.
Back to models