Murf AIInstall

Summary

Generate synthetic speech audio from input text using a specified AI voice, with optional control over voice style, language locale, audio format, and additional audio parameters.

Inputs

• Text (required) — The text to convert into speech. Supports tags like [pause 1s] for controlling speech timing.
• Voice (required) — The AI voice to use for synthesis, selectable from a searchable list or by specifying voice ID.
• Output Locale — The language locale for the generated audio, selectable from a list depending on the voice or by locale code.
• Voice Style — The style of the voice, which varies based on the selected voice and locale.
• Audio Format — The format of the synthesized audio file, such as WAV, MP3, OGG, or others.
• Encode as Base64 — When enabled, returns the audio as a Base64-encoded string instead of a URL.
• Additional Options — Advanced settings including audio duration, channel type, pitch, pronunciation dictionary for custom pronunciations, speech rate, sample rate, variation, and more.

Output shape

a single record containing the generated audio output for each input item

The output includes either a URL to the generated audio file or a Base64-encoded audio string depending on the 'Encode as Base64' option. Optional fields in the output correspond to the chosen parameters and audio synthesis results.