Speech to Text (OpenAI SDK)
Transcribe audio files using the OpenAI SDK-compatible endpoint. Supports all AllModels STT providers. Accepts WAV, MP3, FLAC, MP4/M4A, OGG, and WebM.
Dynamic pricing
audioDuration(body.file)/60*(lower(body.model)=="amazon/amazon-transcribe"?0.00801378:lower(body.model)=="assemblyai/universal-2"?0.00333907:lower(body.model)=="assemblyai/universal-3-5-pro"?0.0046747:lower(body.model)=="assemblyai/universal-3-5-pro-preview"?0.0046747:lower(body.model)=="assemblyai/universal-3-pro"?0.0046747:lower(body.model)=="assemblyai/universal-3-5-pro-realtime"?0.01001722:lower(body.model)=="assemblyai/u3-rt-pro"?0.01001722:lower(body.model)=="assemblyai/universal-streaming-english"?0.00333907:lower(body.model)=="assemblyai/universal-streaming-multilingual"?0.00333907:lower(body.model)=="cartesia/ink-2"?0.00300517:lower(body.model)=="cartesia/ink-whisper"?0.00300517:lower(body.model)=="deepgram/base"?0.01669537:lower(body.model)=="deepgram/enhanced"?0.01936663:lower(body.model)=="deepgram/flux"?0.00868159:lower(body.model)=="deepgram/flux-general-en"?0.00868159:lower(body.model)=="deepgram/flux-general-multi"?0.01041791:lower(body.model)=="deepgram/nova"?0.00788022:lower(body.model)=="deepgram/nova-2"?0.00788022:lower(body.model)=="deepgram/nova-3"?0.00641102:lower(body.model)=="elevenlabs/scribe-v2"?0.00489731:lower(body.model)=="elevenlabs/scribe_v1"?0.00489731:lower(body.model)=="elevenlabs/scribe_v2"?0.00489731:lower(body.model)=="elevenlabs/scribe-v2-realtime"?0.00868159:lower(body.model)=="elevenlabs/scribe_v2_realtime"?0.00868159:lower(body.model)=="fish/transcribe-1"?0.00801378:lower(body.model)=="gemini/gemini-2.5-flash"?0.00256441:lower(body.model)=="gemini/gemini-3-5-transcribe"?0.00667815:lower(body.model)=="gemini/gemini-3.5-transcribe"?0.00667815:lower(body.model)=="gemini/gemini-3-5-transcribe-live"?0.01202067:lower(body.model)=="gemini/gemini-3.5-transcribe-live"?0.01202067:lower(body.model)=="inworld/inworld-stt-1"?0.00333907:lower(body.model)=="openai/gpt-4o-mini-transcribe"?0.00400689:lower(body.model)=="openai/gpt-4o-transcribe"?0.00801378:lower(body.model)=="openai/gpt-4o-transcribe-diarize"?0.00801378:lower(body.model)=="openai/gpt-live-transcribe"?0.02270571:lower(body.model)=="openai/gpt-realtime-whisper"?0.02270571:lower(body.model)=="openai/gpt-transcribe"?0.00601033:lower(body.model)=="openai/whisper-1"?0.00801378:lower(body.model)=="openai/whisper-large-v3"?0.00247092:lower(body.model)=="fal/fal-ai/whisper"?0.00247092:lower(body.model)=="groq/whisper-large-v3"?0.00247092:lower(body.model)=="together/openai/whisper-large-v3"?0.00247092:lower(body.model)=="openai/whisper-large-v3-turbo"?0.00089042:lower(body.model)=="groq/whisper-large-v3-turbo"?0.00089042:lower(body.model)=="openai/whisper-tiny-en"?0.00040069:lower(body.model)=="cloudflare/@cf/openai/whisper-tiny-en"?0.00040069:lower(body.model)=="qwen/qwen3-asr-1-7b"?0.00166954:lower(body.model)=="sprag/rhythm"?0.00166954:lower(body.model)=="qwen/qwen3-asr-flash"?0.00280482:lower(body.model)=="qwen/qwen3-asr-flash-filetrans"?0.00280482:lower(body.model)=="qwen/qwen3-asr-flash-realtime"?0.0072124:lower(body.model)=="soniox/stt-async-v5"?0.00222605:lower(body.model)=="soniox/stt-rt-v5"?0.00267126:lower(body.model)=="soniox/stt-rt-v4"?0.00267126:lower(body.model)=="xai/grok-stt"?0.00222605:lower(body.model)=="grok/grok-stt"?0.00222605:0.02270571)
Example code
// Using @orth/sdk - The simplest way to call APIs
// Install: npm install @orth/sdk
import Orthogonal from "@orth/sdk";
const orthogonal = new Orthogonal({
apiKey: process.env.ORTHOGONAL_API_KEY,
});
const output = await orthogonal.run({
api: "allmodels",
path: "/oai/audio/transcriptions",
body: {
"file": "example",
"model": "example"
}
});
console.log(output);Body parameters
Audio file to transcribe (binary upload)
Model ID, e.g. 'deepgram/nova-3', 'assemblyai/universal-3'
Language code, e.g. 'en'
Response format: json, text, srt, verbose_json, vtt
Timestamp granularity: word, segment