The Speechdash public API is live

The Speechdash public API is available at api.speechdash.com/v1. If you build a product where people need to listen to text, you can create documents and generate speech without opening the browser UI.

What the API does

The REST API mirrors the listening stack in the app:

• Create and manage documents in a user's library (text, title, language)
• Generate speech with the same voice presets, in many languages
• List, read, update, and delete documents as JSON

Documents created through the API appear at speechdash.com. Users can keep listening in the app, edit text, or export audio.

Speech synthesis uses the same cloud voices as in-app playback. Usage comes from the account credit wallet.

Who uses it

Teams reach for the API when listening should live inside another product: an LMS, an internal review tool, or a prototype that needs a spoken preview before a full UI.

If your users already have Speechdash accounts, they keep one wallet and one library. The API is another door, not a second product.

Auth and docs

Create keys under Settings → API. Keys are shown once.

Send Authorization: Bearer sh_live_… on every request. Invalid or revoked keys get a 401.

• API overview
• OpenAPI at api.speechdash.com/v1/openapi.json
• Marketing summary: Public API

Billing

Speech requests hold an estimate, then settle to measured duration. Send an Idempotency-Key on create and speech so a retry does not double-charge.

Rate limits are per account, not per key. Responses include standard rate-limit headers.

First request

1. Sign in and open Settings → API
2. Create a key and copy it immediately
3. Read the API overview
4. POST a short text to /v1/documents, or call /v1/audio/speech with a voice and language

Start with two sentences before you send a chapter.

Related

• Public API
• Getting started
• What uses credits