Skip to content

Inworld Speech to Text

Inworld Speech to Text turns recorded audio files into text: voice notes, call recordings or audio uploaded to the flow. If you don’t set the language, Inworld detects it among the 30 it recognises. It returns one Data per file, with the transcript in the text field.

You need an Inworld API credential with your Inworld account key. See Credentials. The audio is sent to Inworld to be transcribed.

This is not the voice node for calls: to listen to a caller during a live call, the Voice Agent uses the Inworld STT node. This component waits for the whole file.

When to use it

  • Turn voice messages arriving over a messaging channel into text for an agent to read.
  • Transcribe call or meeting recordings to summarise them later.
  • Let an agent transcribe audio when it needs to, using the component as a tool.
  • Transcribe a list of audio files in one go with Batch Mode.

Configuration

FieldWhat it does
API Key (required)Your Inworld key. The key is filled in for you when you choose your Inworld credential.
Audio (required)The audio (or video) file to transcribe: WAV, MP3, OGG, M4A, WEBM… Connect it to the component that brings the file, for example a webhook, a chat with attachments or storage. It accepts several files.
LanguageOptional. The language of the audio, for example es or en. Empty by default: Inworld detects the language.

Advanced options

FieldWhat it does
ModelInworld’s transcription model. Default: inworld/inworld-stt-1, the only one available.

Output

The Data output returns one record per file:

{
"text": "Hola, buenos días. Su cita está confirmada para el martes a las diez y media.",
"language": "es",
"file_name": "voice_note.ogg",
"provider": "Inworld",
"model": "inworld/inworld-stt-1"
}

Inworld does not return the language it detected: language is the one you set in Language, and it stays empty if you leave that blank.

Each file can be up to about 16 MB. If one is larger, the run stops with a message giving its size.

Example

A clinic receives WhatsApp voice notes from patients who want to change their appointment. The flow passes each audio to Inworld Speech to Text with Language set to es. An agent reads the text field, finds the patient’s appointment and offers a new slot.

Tips

  • If you know the language of the audio, set it in Language: the language field of the output is then filled in.
  • Measured in our test environment on 3 November 2026: the sentence “Hola, buenos días. Su cita está confirmada para el martes a las diez y media.” was transcribed in 0.5 s, word for word.