Text to Speech (OpenAI SDK)
Generate speech audio from text using the OpenAI SDK-compatible endpoint. Supports all AllModels TTS providers. Returns binary audio in the requested format (mp3, opus, aac, flac, wav, pcm).
Dynamic pricing
length(body.input)/1000*(lower(body.model)=="amazon/amazon-polly-generative"?0.0400689:lower(body.model)=="amazon/amazon-polly-long-form"?0.133563:lower(body.model)=="amazon/amazon-polly-neural"?0.02137008:lower(body.model)=="amazon/amazon-polly-standard"?0.00534252:lower(body.model)=="canopylabs/orpheus-3b"?0.02003445:lower(body.model)=="canopylabs/orpheus-3b-0.1-ft"?0.02003445:lower(body.model)=="together/canopylabs/orpheus-3b-0.1-ft"?0.02003445:lower(body.model)=="canopylabs/orpheus-arabic-saudi"?0.0534252:lower(body.model)=="groq/canopylabs/orpheus-arabic-saudi"?0.0534252:lower(body.model)=="canopylabs/orpheus-v1-english"?0.02938386:lower(body.model)=="groq/canopylabs/orpheus-v1-english"?0.02938386:lower(body.model)=="cartesia/sonic-3"?0.04992585:lower(body.model)=="together/cartesia/sonic-3"?0.04992585:lower(body.model)=="cartesia/sonic-3-5"?0.04992585:lower(body.model)=="cartesia/sonic-3.5"?0.04992585:lower(body.model)=="cartesia/sonic-3-6"?0.04992585:lower(body.model)=="cartesia/sonic-3.6"?0.04992585:lower(body.model)=="deepgram/aura"?0.02003445:lower(body.model)=="deepgram/aura-2"?0.0400689:lower(body.model)=="elevenlabs/eleven-flash-v2"?0.0667815:lower(body.model)=="elevenlabs/eleven_flash_v2"?0.0667815:lower(body.model)=="elevenlabs/eleven-flash-v2-5"?0.0667815:lower(body.model)=="elevenlabs/eleven_flash_v2_5"?0.0667815:lower(body.model)=="elevenlabs/eleven-multilingual-v2"?0.133563:lower(body.model)=="elevenlabs/eleven_multilingual_v2"?0.133563:lower(body.model)=="elevenlabs/eleven-turbo-v2"?0.0667815:lower(body.model)=="elevenlabs/eleven_turbo_v2"?0.0667815:lower(body.model)=="elevenlabs/eleven-turbo-v2-5"?0.0667815:lower(body.model)=="elevenlabs/eleven_turbo_v2_5"?0.0667815:lower(body.model)=="fal/fal-ai/elevenlabs/tts/turbo-v2.5"?0.0667815:lower(body.model)=="elevenlabs/eleven-v3"?0.133563:lower(body.model)=="elevenlabs/eleven_v3"?0.133563:lower(body.model)=="fal/fal-ai/elevenlabs/tts/eleven-v3"?0.133563:lower(body.model)=="fish/s1"?0.02003445:lower(body.model)=="fish/s2-1-pro"?0.02003445:lower(body.model)=="fish/s2.1-pro"?0.02003445:lower(body.model)=="fish/s2-pro"?0.02003445:lower(body.model)=="gemini/gemini-2-5-flash-tts"?0.05609646:lower(body.model)=="gemini/gemini-2.5-flash-preview-tts"?0.05609646:lower(body.model)=="gemini/gemini-2-5-pro-tts"?0.11219292:lower(body.model)=="gemini/gemini-2.5-pro-preview-tts"?0.11219292:lower(body.model)=="gemini/gemini-3-1-flash-tts-preview"?0.11219292:lower(body.model)=="gemini/gemini-3.1-flash-tts-preview"?0.11219292:lower(body.model)=="hexgrad/kokoro-82m"?0.0133563:lower(body.model)=="hexgrad/kokoro-82m"?0.0133563:lower(body.model)=="together/hexgrad/kokoro-82m"?0.0133563:lower(body.model)=="inworld/inworld-tts-2"?0.03339075:lower(body.model)=="inworld/inworld-tts-2-flash"?0.02003445:lower(body.model)=="minimax/speech-01-hd"?0.133563:lower(body.model)=="minimax/speech-01-turbo"?0.0801378:lower(body.model)=="minimax/speech-02-hd"?0.133563:lower(body.model)=="minimax/speech-02-turbo"?0.0801378:lower(body.model)=="minimax/speech-2-8-hd"?0.133563:lower(body.model)=="fal/fal-ai/minimax/speech-2.8-hd"?0.133563:lower(body.model)=="minimax/speech-2.8-hd"?0.133563:lower(body.model)=="minimax/speech-2-8-turbo"?0.0801378:lower(body.model)=="fal/fal-ai/minimax/speech-2.8-turbo"?0.0801378:lower(body.model)=="minimax/speech-2.8-turbo"?0.0801378:lower(body.model)=="minimax/speech-2.6-hd"?0.133563:lower(body.model)=="minimax/speech-2.6-turbo"?0.0801378:lower(body.model)=="myshell-ai/melotts"?0.00029681:lower(body.model)=="cloudflare/@cf/myshell-ai/melotts"?0.00029681:lower(body.model)=="openai/gpt-4o-mini-tts"?0.02230502:lower(body.model)=="openai/tts-1"?0.02003445:lower(body.model)=="openai/tts-1-hd"?0.0400689:lower(body.model)=="qwen/qwen3-tts-12hz-1-7b-customvoice"?0.02163721:lower(body.model)=="sprag/chorus-voices"?0.02163721:lower(body.model)=="soniox/tts-rt-v2"?0.01883238:lower(body.model)=="soniox/tts-rt-v1"?0.01883238:lower(body.model)=="xai/grok-tts"?0.02003445:lower(body.model)=="grok/grok-tts"?0.02003445:0.133563)
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/speech",
body: {
"model": "example",
"input": "example",
"voice": "example"
}
});
console.log(output);Body parameters
Model ID, e.g. 'elevenlabs/eleven_turbo_v2_5', 'deepgram/aura-2', 'cartesia/sonic'
The text to generate audio for
Voice ID, e.g. 'alloy', 'AM:@narrator', or a provider voice ID
Audio format: mp3, opus, aac, flac, wav, pcm. Default: mp3
Speed multiplier (0.25 to 4.0). Not all providers support speed control.