Basic Information

appmixer.ai.deepgram.TextToSpeech

Text to Speech

1.0.0

Public

Generates speech audio from text using Deepgram Aura-2 and stores the result in File Storage, returning a file ID. Text is limited to 2000 characters per request.

Input Ports

in

FieldTypeDescription
Text textarea The text to convert to speech. Maximum 2000 characters.
Voice text The Aura voice to use, e.g. aura-2-thalia-en. Start typing to pick from the TTS voices, or enter a model name manually.
Encoding select Output audio encoding. Compressed encodings (mp3, opus, flac, aac) are REST-only.
Container text Optional container format, e.g. wav or ogg.
Sample Rate select Output sample rate in Hz.
Bit Rate number Optional bit rate for compressed encodings.
File Name text Optional name for the generated audio file in File Storage.

Output Ports

out

FieldTypeDescription
File ID string -
File Name string -
Content Type string -
Character Count integer -

Full Metadata