Kokoro
Kokoro is an open-weight text voiceover (TTS) model with 82 million parameters. Thanks to its lightweight architecture, it is faster and cost-effective compared to large models. As an infrastructure, ⁇ misaki ⁇ uses the G2P library and can be installed via PyPI.
Kokoro
55hexgrad · AI Call Agents & Telephony
Common commercial products in this category: Vapi, Bland AI, Retell AI
- You include the library in your project using Pip
- Run with basic or advanced code blocks on Google Colab
- You convert text into sound using different language codes
- • Last update over 1 year ago
- • NeutralHacker News
Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
“Kokoro voices were the non-human actors directed by Opus, featured in the sound performance "God Bless the United States of Aliens". A theatrical adaptation of a liturgical texts, a surveilled mass ceremony at a protesting Christian church, being exhibited at the 61st Venice…”
- ↑ PositiveHacker News
Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
“I love Kokoro. I use it to read ebooks that don't have audiobooks and it works pretty good for that. I have a Python script that reads epub/html, runs the model and writes mp3s. Kokoro supports a limited number of languages. I've had to resort to other models to support Dutch,…”
My note
Alternative pages
More in: AI Call Agents & Telephony
- LangChain★ 148,748 · today
- Whisper (OpenAI)★ 111,613 · 2 mo ago
- Bark★ 39,290 · 2 yr ago
- faster-whisper★ 26,343 · today
- Pipecat★ 16,955 · today
- F5-TTS★ 15,491 · 7 days ago