AssemblyAI's voice cloning tips: WAV audio, 15–25 seconds of reference speech
AssemblyAI · x · 2026-10-29
AssemblyAI's team shares practical tips for accurate voice clones:
- Use WAV, not MP3 — avoid lossy compression artifacts;
- Provide 15–25 seconds of reference audio (docs support 10–30s from recordings under 2 minutes);
- Try both scripted and unscripted samples to see which fits your use case;
- Pick the mic that matches your target scenario.
The docs also note clones require speaker consent, remain usable for 60 days unless consent is renewed, and are private to the creating account.
More from Multimodal
- Generating K-Pop music videos with a Claude Music Video skill, no MCP needed — AIandDesign · 2026-10-29
- Granary-v2 open speech model expands to 48 languages with open data and pipeline — rdesh26 · 2026-10-29
- ciguleva shares surreal AI artwork "Under the Hood of the Universe" — ciguleva · 2026-10-29
- ComfyUI Halloween workflow turns any image into a carved pumpkin video — PurzBeats · 2026-10-29
- NVIDIA FastGen ships major update: FLUX.2, LTX-2.5, Cosmos 3 plus four new acceleration methods — ArashVahdat · 2026-10-29
- Shading and lighting upgrade teased for AI-generated slop_eisley project — jasonkneen · 2026-10-29