Convert input text into speech audio using HeyGen Starfish TTS.
npx skills add https://github.com/hanzoai/video --skill text-to-speech-hanzoai
Please help me install this Agent Skill. Skill: text-to-speech Source: https://github.com/hanzoai/video/tree/main/.agents/skills/text-to-speech Command: npx skills add https://github.com/hanzoai/video --skill text-to-speech-hanzoai
Text-to-speech generation for narration, voiceovers, and accessibility, turning written content into spoken audio.
Provide the text you want spoken and choose a voice to generate the audio.
High-intent search queries and answers about installing and using this skill.
You can convert text into natural-sounding speech by providing your input text to the HeyGen Starfish TTS engine and selecting a preferred voice to generate spoken audio.
Yes, you can customize voice generation by adjusting speed, pitch, and locale settings to suit your specific language and tone requirements for multilingual voiceovers.
Yes, an API key is required to authenticate requests when accessing the HeyGen Starfish TTS endpoints to generate speech audio from text.
The text-to-speech process returns an audio_url containing the generated speech and the duration of the audio file for your narration project.
Generating speech audio is ideal for standalone narration in videos, podcasts, training content, and accessibility applications where written content needs to be spoken aloud.
You can retrieve available voices by calling the GET /v1/audio/voices endpoint to list and choose a voice before generating your speech audio.
gyalamanch001aGenerate speech audio from text using HeyGen Starfish TTS.
doany-aiGenerate Wan 2.7 videos from text prompts via RunComfy CLI.
ChronoAIProjectGenerates short videos from ChatGPT images with ffmpeg and text-to-speech audio.
kaivyyTranscribe audio files with OpenAI Whisper and synthesize speech from text.
