Quickstart
Make your first text-to-speech and speech-to-text requests with AllModels.
Use the SDK you already know
AllModels works with the official ElevenLabs and OpenAI SDKs. Set the base URL to https://api.allmodels.io/el or https://api.allmodels.io/oai and use your AllModels API key.
Install an SDK
Install the ElevenLabs JavaScript SDK
npm install @elevenlabs/elevenlabs-jsConfigure a client
Configure the ElevenLabs Python client
from elevenlabs.client import ElevenLabs
API_BASE = "https://api.allmodels.io/el"
allmodels_api_key = "YOUR_ALLMODELS_API_KEY"
client = ElevenLabs(
api_key=allmodels_api_key,
base_url=API_BASE,
)Text to speech
import { writeFile } from "node:fs/promises";const response = await fetch("https://api.allmodels.io/oai/audio/speech", { method: "POST", headers: { Authorization: `Bearer ${process.env.ALLMODELS_API_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "elevenlabs/eleven_flash_v2_5", "voice": "21m00Tcm4TlvDq8ikWAM", "input": "Hello from AllModels", "response_format": "mp3"})});if (!response.ok) throw new Error(`AllModels request failed: ${response.status}`);await writeFile("speech.mp3", Buffer.from(await response.arrayBuffer()));Speech to text
import { readFile } from "node:fs/promises";const form = new FormData();form.set("file", new Blob([await readFile("call.wav")]), "call.wav");form.set("model", "deepgram/nova-3");form.set("response_format", "json");const response = await fetch("https://api.allmodels.io/oai/audio/transcriptions", { method: "POST", headers: { Authorization: `Bearer ${process.env.ALLMODELS_API_KEY}`, }, body: form});if (!response.ok) throw new Error(`AllModels request failed: ${response.status}`);console.log(await response.json());Next steps
You can now generate and transcribe audio. Continue with streaming, model selection, or the complete API reference.
- Streaming & realtime: build low-latency TTS and realtime transcription flows.
- Models: browse available TTS and STT models.
- Providers: choose which providers serve your requests.
- Voices: find voices supported by each provider.
- Text to speech: generate audio with
POST /el/v1/text-to-speech/{voice_id}. - Speech to text: transcribe uploaded audio with
POST /el/v1/speech-to-text. - API Reference: explore every endpoint, field, response, and code example.