BifrostAPI
Models/ElevenLabs/eleven-flash
E
ElevenLabs
NEW

ElevenLabs Flash

TextAudio
Synthesis
$7.00
/ 10K chars

ElevenLabs Flash is a low-latency text-to-speech model (~75ms) covering 32 languages — suited to real-time dialogue and in-game voice. Call POST /v1/audio/speech; `voice` takes an ElevenLabs voice_id and may be omitted for the default. Billed on the characters you send, so the price is known before the call.

Quick start

How to call

POST /v1/audio/speech
bash
curl https://conduit-api.bifrostapi.net/v1/audio/speech \
  -H "Authorization: Bearer ck-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"eleven-flash","input":"你好,世界"}' \
  --output out.mp3

→ Returns binary audio (audio/mpeg). Runs on the default voice; add "voice" with an ElevenLabs voice_id to choose another.

Auth, billing & streaming → Quickstart

More from ElevenLabs