One API for every voice workload

Enterprise voice infrastructure, behind a single API key.

Text to speech, speech to text, speech recognition and voice cloning — production-ready endpoints, usage tracking and an interactive playground your engineers can try today.

Try the playground Get an API keyView documentation

Products

Text to Speech

Turn text into natural speech across a catalogue of production voices.

POST /v1/text-to-speech

Speech to Text

Transcribe mp3, wav, m4a, webm and ogg with automatic language detection.

POST /v1/speech-to-text

Speech Recognition

A dedicated ASR surface for recognition workloads, same low latency.

POST /v1/asr

Voice Cloning

Create a custom voice from a short sample, with consent recorded on every clone.

POST /v1/voices/clone

How it works

01

Create an account

Register and get an organization provisioned automatically.

02

Generate an API key

One click. The secret is shown once and stored hashed.

03

Call the API

One bearer token across every voice endpoint. No SDK required.

Built for developers

Bearer authentication, predictable JSON errors, and a request ID on every response.

curl -X POST https://your-domain.com/api/v1/text-to-speech \
  -H "Authorization: Bearer vp_live_xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{"text":"Hello from the Voice API Platform.","voice_id":"voice_xxxxx"}' \
  --output speech.mp3

Talk to us about enterprise

Volume pricing, dedicated capacity and procurement support for teams deploying voice at scale.

Start building