Yes. ElevenLabs offers Voice Changer (formerly “speech‑to‑speech”), which converts a recorded source voice into a different target/cloned voice while preserving timing, emotion, and delivery—ideal for giving one performance multiple character voices. (help.elevenlabs.io)
How you can use it
Web app: Record directly in the browser or upload audio, pick any voice from the library (or your own cloned voice), then generate and download the conversion. (elevenlabs.io)
API: Send an audio file to POST /v1/speech-to-speech/:voice_id with options like model_id, voice_settings, and remove_background_noise. The endpoint returns the converted audio. (elevenlabs.io)
Key details
Max input length: 5 minutes per request (split longer material into chunks). (help.elevenlabs.io)
Pricing: Billed at 1,000 credits (≈1,000 characters) per minute of processed audio. (help.elevenlabs.io)
Formats: Accepts common audio (MP3, M4A, FLAC, OGA/OGG, WAV) and video (MKV, WEBM, MP4, MOV) inputs. (help.elevenlabs.io)
Languages: Multilingual STS v2 supports 29 languages; you can also use the English STS model. (elevenlabs.io)
Performance: The product supports rapid processing and live recording in the browser; marketing materials note response times as low as ~400 ms for short generations. (elevenlabs.io)
Bottom line: If you record your own voice, you can convert that performance into different target voices (i.e., different “characters”) in the app or via the API. Note that the API converts uploaded/recorded audio rather than offering a persistent real‑time streaming pass‑through. (elevenlabs.io)
nova void
noble belfry