ElevenLabs

Use ElevenLabs’ text-to-speech, speech-to-text, and voice cloning APIs through Portkey.

ElevenLabs provides industry-leading text-to-speech, speech-to-text, dubbing, and voice cloning capabilities. Portkey allows you to use ElevenLabs’ APIs with full observability and reliability features.

The unified /v1/audio/speech and /v1/audio/transcriptions endpoints route to ElevenLabs’ text-to-speech and speech-to-text APIs directly, without any custom host configuration.

Quick Start

Text to Speech

Generate speech from text using the ElevenLabs TTS API:

cURL

curl -X POST https://api.portkey.ai/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "x-portkey-provider: @YOUR_ELEVENLABS_PROVIDER_SLUG" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -d '{
    "model": "eleven_multilingual_v2",
    "input": "Hello! Welcome to Portkey.",
    "voice": "21m00Tcm4TlvDq8ikWAM"
  }' \
  --output speech.mp3

voice accepts any ElevenLabs voice id (premade, cloned, or custom) — it is forwarded as-is rather than remapped from OpenAI’s built-in voice names.

Speech to Text

Transcribe audio using ElevenLabs’ Scribe model:

cURL

curl -X POST https://api.portkey.ai/v1/audio/transcriptions \
  -H "x-portkey-provider: @YOUR_ELEVENLABS_PROVIDER_SLUG" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -F file="@recording.mp3" \
  -F model="scribe_v1"

Add Provider in Model Catalog

Before making requests, add ElevenLabs to your Model Catalog:

1. Go to Model Catalog → Add Provider
2. Select ElevenLabs
3. Enter your ElevenLabs API key
4. Name your provider (e.g., elevenlabs)

Complete Setup Guide

See all setup options and detailed configuration instructions

---

Using with Portkey SDK

Python

from portkey_ai import Portkey

portkey = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="@YOUR_ELEVENLABS_PROVIDER_SLUG"
)

Other ElevenLabs APIs — voice cloning, dubbing, and voice design — aren’t covered by the unified /v1/audio/* endpoints yet. Reach those through the custom host pattern with x-portkey-custom-host: https://api.elevenlabs.io and your xi-api-key.

---

ElevenLabs Features

ElevenLabs offers advanced audio AI capabilities:

• Text to Speech: Convert text to natural-sounding speech in 29+ languages
• Speech to Text: Transcribe audio with high accuracy
• Voice Cloning: Clone voices from audio samples
• Dubbing: Automatically dub audio/video content across languages
• Voice Design: Generate unique AI voices

ElevenLabs API Documentation

Explore the complete ElevenLabs API documentation

---

Next Steps

Gateway Configs

Add retries and timeouts for audio processing

Observability

Monitor and trace your ElevenLabs requests

Custom Host Setup

Learn more about custom host configuration

Metadata

Add custom metadata to track audio sources

For complete SDK documentation:

SDK Reference

Complete Portkey SDK documentation

---

Portkey is now PRISMA AIRS AI Gateway. See it in action.

Contact Us