Transform audio timbre into a target voice while preserving prosody via ElevenLabs API.
npx skills add https://github.com/ri-ru/cyrano --skill voice-changer-ri-ru
Please help me install this Agent Skill. Skill: voice-changer Source: https://github.com/ri-ru/cyrano/tree/main/.agents/skills/voice-changer Command: npx skills add https://github.com/ri-ru/cyrano --skill voice-changer-ri-ru
This skill solves the challenge of changing the speaker of an existing audio recording without losing the original emotion, pacing, or delivery.
Use the voice-changer skill to convert the audio file source.mp3 into the voice of George using the ElevenLabs API.
High-intent search queries and answers about installing and using this skill.
Speech-to-speech voice conversion transforms audio timbre into a target voice while preserving the original prosody, including laughs, whispers, and intonation. This maintains the speaker's emotional delivery and pacing during the voice swap.
Yes, you can use the ElevenLabs API for voice-over dubbing and localization. It converts source audio into a target voice in different languages while maintaining the original performance and emotional delivery.
Yes, an ElevenLabs API key is required to perform speech-to-speech audio processing. You must provide this key to authenticate your requests when transforming audio recordings into a target voice.
The voice conversion process supports various audio formats for speech-to-speech processing. You can use these formats for tasks like speaker anonymization in sensitive recordings while keeping the original cadence.
The best way to re-voice a scratch narration track is using speech-to-speech conversion. This technique swaps the original speaker's timbre with a professional character voice while preserving the original pacing and delivery.
When anonymizing a speaker in sensitive audio recordings, limitations depend on the ElevenLabs API processing capabilities. The conversion preserves the original cadence, but complex audio with heavy background noise may affect the voice swap quality.
QcasaresTranscribe audio to text using ElevenLabs' Scribe v2 API.
mu-zi-leeConvert long-form text into structured JSON dubbing scripts for Qwen3-TTS.
aztr0nutzsGenerate speech, transcribe audio, clone voices, and dub audio via the ElevenLabs API.
X-School-AcademyGenerate speech audio from text with customizable voice characteristics.
