OpenAI: Whisper Tiny English
openai/whisper-tiny-en
Free
active
stt
1 provider
Beta English-only Whisper Tiny speech-recognition model served through Cloudflare Workers AI.
AuthorOpenAI
Languages1 languages
Statusactive
Providers
Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.
ProviderSlugPriceLatencyiFor TTS, latency is measured as time to first byte of audio. For STT, latency is measured as time to first token.ModesUptime
Cloudflare Workers AI
1 params
cloudflare
Not priced
—
Synchronous
Supported languages
1 languages
English
en
Features
Synchronous
Transcribes a fully-submitted audio file in a single synchronous request.
synchronous
Word timestamps
Returns word-level transcription records in the words response field.
word_timestamps
WebVTT
Returns a WebVTT transcript in the vtt response field.
webvtt
Code
ElevenLabs SDK streaming STT
Streams microphone or file audio through the ElevenLabs-compatible allmodels route.
import { ElevenLabsClient } from "elevenlabs";
const client = new ElevenLabsClient({
apiKey: process.env.ALLMODELS_API_KEY,
baseUrl: "https://api.allmodels.io/el"
});
const connection = await client.speechToText.realtime.connect({
modelId: "openai/whisper-tiny-en",
languageCode: "en"
}, {
queryParams: {
provider: {
"only": [
"cloudflare"
]
}
}
});
// Send audio frames to connection, then handle transcript events.