Text to Speech turns a short text into an audio clip: type or paste the text, pick a voice, generate, download. It is made for clips of up to 1,500 characters. For longer texts and books use Audio Studio. It supports more than 130 languages, with particular care for Arabic: diacritics, dialects, numbers and abbreviations.
What it offers
- Voices: the voice library, your cloned voices and your team's voices.
- Output in the web app: MP3 or WAV; the API offers more formats.
- Uses: voiceovers for videos and ads, announcements, social clips, e-learning snippets, and spoken replies in apps through the API.
The two engines
- Standard: studio voices, your cloned voices and full voice settings, with three modes: emotion and dialect (the default), quality emotion and dialect, and Studio Quality.
- Advanced: its own set of voices, directed in plain words through the Context box. It is enabled per deployment, so it may not always be available.
Cost
Credits depend on the number of characters, the text processing option, the voice (some voices carry a fee) and the mode or engine. The estimate is always shown before generating. Current rates are on the pricing page. Text sent for conversion is checked automatically against the content policy.
For details see the Text to Speech documentation or the Text to Speech page. Developers can start with getting started with the API.