Changelog

API: `GET /v1/voices` returns an object envelope

GET /v1/voices now returns an object envelope instead of a bare JSON array, so the list can carry pagination and future sibling fields without another breaking change. Before (pin 2026-06-26 or…

API version pinning with `Speechify-Version`

The API now supports date-based version pinning with the Speechify-Version request header. Current version: 2026-06-25 Header format: YYYY-MM-DD Resolution order: request header, workspace default,…

Docs: response-streaming behaviour on `POST /v1/audio/stream` clarified

The documentation for POST /v1/audio/stream now describes the endpoint's response shape accurately: The response body is the raw audio bytes delivered over HTTP chunked transfer encoding. There is no…

API: New `simba-3.0` streaming model

simba-3.0 is now available on POST /v1/audio/speech and POST /v1/audio/stream via the model field. It's the new streaming-native voice model with lower TTFB and richer expressivity, including direct…

New API Domain: api.speechify.ai

The Speechify API is now available at https://api.speechify.ai.

API: Concurrency Limits for TTS Endpoints

We've introduced concurrency limits to prevent abuse and ensure fair usage across all users. These limits restrict the number of simultaneous in-flight text-to-speech requests per user.

API: Differentiated Rate Limits for Free and Paid Users

We've introduced differentiated rate limiting based on user plan type to ensure fair usage and optimal performance for all users.

API: Added Support for PCM Audio Format

Support for the PCM audio format is now available for both the Speech and Stream endpoints.

SDK: New Typescript SDK

We've published a new Typescript SDK. Try it out: npm install @speechify/apiTogether with the release, the old @speechify/api-sdk package is now deprecated.

API: Deprecated POST /v1/auth/token endpoint

The POST /v1/auth/token endpoint is now deprecated. We will only support API Key authentication moving forward.

API: Download Personal Voice Sample

We've added a new endpoint to download personal cloned voice sample file

API: Text Normalization

We've added a new option to the API to normalize the text. If enabled, it will transform numbers, dates, etc. into words. For example, "55" is normalized into "fifty five". This can increase latency…

API: Loudness Normalization Update

Previously, the loudness normalization was enabled by default. Now it's disabled by default as we believe, together with our internal model improvements, it will improve the overall quality of the…

SDK: Python

We've released a new Python SDK. Checkout the repository for more information.

API: Locale support for personal voices

When creating a personal voice, the locale can be specified. Please refer to the full API reference.

API: Streaming format fallback

Streaming endpoint now defaults to audio/mpeg when the Accept header is not provided or is invalid.

API: Voices avatar and gender support

When cloning the voice, avatar and gender can be specified. Please refer to the full API reference.

Playground: Added Unpaid Invoice Warning

We've added a warning to the sidebar and Subscription Details page to notify you of any unpaid invoices.

Playground: Filters added to Voices page

We've added filters to the Voices page, allowing you to filter voices by language, gender, and other attributes.

Billing: Changed billing cycle start date

We've changed the default billing start day from 1st of the month to the date when a subscription is started.