Skip to content
Documentation
Contact
← Back to documentation
Technical Reference

Hume AI

Hume AI integration for Flows360 workflows.

CategoryArtificial Intelligence
Authenticationcustom
Version0.1.7
Published scopes0 published scopes
Last updatedSeptember 30, 2026

Overview

Connect Hume AI with Flows360

Hume AI integration for Flows360 workflows.

Use the Hume AI connector to include its declared actions and events in Flows360 workflows without duplicating the integration logic inside each consuming system. This pinned connector version currently exposes 6 actions and 1 trigger.

Available actions

  • Generate Text to Speech
  • Generate Speech from File
  • Create Voice
  • Delete Voice
  • Analyze Emotions from URL
  • Get Emotion Results

Available triggers

  • New Voice

The capability list above is generated from the exact reviewed connector package so the public description stays aligned with the version Flows360 operates.

Technical guide

Technical reference

Package identity

  • Connector: Hume AI
  • Package: @activepieces/piece-hume-ai@0.1.7
  • Exact artifact digest: sha256:554eccd7daa7cafcf8c302b0e7ed3ed50d817d44a5963051ecf417be86c9830d
  • Runtime: Activepieces-compatible deterministic worker
  • Source: the exact reviewed Activepieces source

Authentication

SECRET TEXT. Connection values are tenant-specific and remain in the consuming Studio instance; CDK stores definitions and field metadata, not customer credential values.

Action contracts

  • Generate Text to Speech (generate_text_to_speech), Convert text to speech using Hume AI's expressive text-to-speech technology Classification: read.
  • Generate Speech from File (generate_speech_from_file), Convert audio file to speech using Hume AI's expressive text-to-speech technology Classification: read.
  • Create Voice (create_voice), Save a custom voice to your account using a TTS generation ID Classification: read.
  • Delete Voice (delete_voice), Delete a custom voice from your account Classification: read.
  • Analyze Emotions from URL (analyze_emotions_from_url), Start a batch emotion analysis job for media files hosted at URLs Classification: read.
  • Get Emotion Results (get_emotion_results), Retrieve emotion analysis predictions from a completed batch job Classification: read.

Trigger contracts

  • New Voice, polling.

Verification

Runtime execution evidence is managed separately from package metadata.

Capability summary

Authenticationcustom
Supported objects7
Supported actions6
Triggers1

Authentication

Authentication method: custom

Authentication profiles

connection · custom
  • API Key Required · protected credential

Supported objects

ObjectReadWriteNotes
Generate Text to Speech Yes No Convert text to speech using Hume AI's expressive text-to-speech technology
Generate Speech from File Yes No Convert audio file to speech using Hume AI's expressive text-to-speech technology
Create Voice Yes No Save a custom voice to your account using a TTS generation ID
Delete Voice Yes No Delete a custom voice from your account
Analyze Emotions from URL Yes No Start a batch emotion analysis job for media files hosted at URLs
Get Emotion Results Yes No Retrieve emotion analysis predictions from a completed batch job
New Voice Yes No polling trigger declared by the pinned package.

Supported actions

Generate Text to Speech · Read

Convert text to speech using Hume AI's expressive text-to-speech technology

generate_text_to_speech · Risk: low · Retry: safe

Inputs

  • text · string · Required, The text to convert to speech
  • voiceDescription · string · Optional, Natural language description of how the speech should sound (tone, accent, style, etc.). If no voice is specified, this will generate a dynamic voice.
  • format · string · Required, The output audio file format
  • speed · number · Optional, Speed multiplier for the synthesized speech (0.75-1.5 recommended)
  • numGenerations · number · Optional, Number of audio generations to produce (1-5 recommended)
  • contextText · string · Optional, Optional context text to influence speech style and prosody consistency
  • contextDescription · string · Optional, Description for the context text (how it should sound)
  • trailingSilence · number · Optional, Duration of silence to add at the end of the speech
  • splitUtterances · boolean · Optional, Automatically split text into natural-sounding speech segments
Generate Speech from File · Read

Convert audio file to speech using Hume AI's expressive text-to-speech technology

generate_speech_from_file · Risk: low · Retry: safe

Inputs

  • text · string · Required, The text to convert to speech
  • voiceDescription · string · Optional, Natural language description of how the speech should sound (tone, accent, style, etc.). If no voice is specified, this will generate a dynamic voice.
  • format · string · Required, The output audio file format
  • speed · number · Optional, Speed multiplier for the synthesized speech (0.75-1.5 recommended)
  • contextText · string · Optional, Optional context text to influence speech style and prosody consistency
  • contextDescription · string · Optional, Description for the context text (how it should sound)
  • trailingSilence · number · Optional, Duration of silence to add at the end of the speech
  • splitUtterances · boolean · Optional, Automatically split text into natural-sounding speech segments
Create Voice · Read

Save a custom voice to your account using a TTS generation ID

create_voice · Risk: low · Retry: safe

Inputs

  • generationId · string · Required, The unique ID from a previous TTS generation to save as a custom voice
  • voiceName · string · Required, A descriptive name for your custom voice
Delete Voice · Read

Delete a custom voice from your account

delete_voice · Risk: low · Retry: safe

Inputs

  • voiceName · string · Required, The name of the custom voice to delete
Analyze Emotions from URL · Read

Start a batch emotion analysis job for media files hosted at URLs

analyze_emotions_from_url · Risk: low · Retry: safe

Inputs

  • urls · array · Required, URLs to media files to analyze (images, videos, audio). Supports up to 100 URLs or archives (.zip, .tar.gz)
  • models · object · Optional, Specify which models to use for inference. Leave empty to run all models.
  • transcription · boolean · Optional, Include speech-to-text transcription in the analysis
  • callbackUrl · string · Optional, Optional webhook URL to receive results when the job completes
  • notify · boolean · Optional, Send email notification upon job completion or failure
Get Emotion Results · Read

Retrieve emotion analysis predictions from a completed batch job

get_emotion_results · Risk: low · Retry: safe

Inputs

  • jobId · string · Required, The ID of the emotion analysis job to retrieve results for

Triggers

New Voice · Poll

Triggers when a new voice is created in Hume AI

Setup

Setup

  1. Add the Hume AI connector to the workflow in the target Flows360 Studio instance.
  2. Create or select the tenant-specific connection required by the connector. Connection secrets remain in the Studio connection boundary and are not copied into CDK documentation.
  3. Provide the connection fields declared by the pinned package:
  • No provider credential fields are declared by the pinned package.
  1. Select the required action or trigger and complete its declared input fields. Required and optional inputs are defined by the exact package schema.
  2. Test the workflow in the appropriate environment before enabling production scheduling or event delivery.

Limitations

Limitations and operational notes

  • This content describes @activepieces/piece-hume-ai@0.1.7; provider behaviour can change independently and should be revalidated when the provider or connector version changes.
  • Only the 6 actions and 1 trigger declared by this pinned package are represented here.
  • Tenant credentials and connection values are not stored in the public connector record.
  • Provider-side permissions, account entitlements, quotas and rate limits remain subject to the connected provider account and are not inferred when the package does not declare them.
  • Runtime execution evidence is managed separately from package metadata.

Troubleshooting

Why canu2019t the connector authenticate?

Check the tenant connection in Studio and confirm every required Hume AI connection field is present. Re-authorise OAuth-based connections if the provider token or consent has expired. Do not place credential values in CDK content or logs.

Why is an action or trigger unavailable?

Confirm that the workflow is using @activepieces/piece-hume-ai@0.1.7 and compare the requested capability with the declared action and trigger list for this version. A capability that is not declared by the pinned package should not be presented as supported.

What should I check after a provider-side change?

Revalidate authentication, required fields, action/trigger behaviour and provider documentation before publishing refreshed connector content or moving a new package version into production.

github.com