Actions16
- LLM (Text Generation) Actions
- Image Generation Actions
- Video Generation Actions
- Text-to-Speech Actions
- Speech-to-Text Actions
- Music Generation Actions
- Embeddings Actions
- Content Moderation Actions
- Custom Inference Actions
Text-to-Speech → Generate Speech
AI-generatedSummary
Convert input text into synthesized speech audio using a selected Chutes.ai text-to-speech chute.
Inputs
- Chute — Select a specific text-to-speech chute URL or enter a custom chute URL for speech generation.
- Text (required) — The text string to convert into speech.
- Voice — Choose a predefined voice from a categorized list or use the chute's default voice. Selecting 'Custom' allows specifying a custom voice name or ID.
- Custom Voice — Specify a custom voice name or ID if the 'Custom' voice option is selected.
- Additional Options — Optional settings including speech speed multiplier and maximum timeout in seconds for audio generation.
Output shape
a single binary audio file or, in cases where the API returns a URL or JSON, a JSON object containing the audio information.
The operation requests speech audio from the chute's /speak endpoint, returning binary audio data (commonly MP3) attached to the output item in binary property. If the voice selection is an invalid separator, the chute's default voice is used. The operation supports a maximum timeout after which it errors, suitable for long texts. This output can be used in workflows requiring synthesized speech audio from arbitrary input text.
Examples
Example 1: Generate speech audio from input text using a selected Kokoro model chute with 'af_bella' voice and a speed of 1x. The output is an MP3 audio file attached to the workflow item.
Set 'Chute' to a TTS chute URL or keep default. Enter desired text in 'Text'. Select 'af_bella' under 'Voice'. Adjust 'Speed' to 1 in additional options if needed.