Echolancer · Text‑to‑Speech Samples Lightweight, finetune‑friendly (soon) TTS. Below are curated samples across voices and prompts. Grab the code, read the write‑up, or try it in Colab. GitHub …

Echolancer Echolancer is a multi-speaker, transformer decoder-only English TTS model. We use NeuCodec as the audio tokenizer. We (me and my cat) release pretrained checkpoints, notebooks, …

echolancer-v0.1-base ... Echolancer-v0.1-base This is a TTS model pretrained on the pre-tokenized Emilia dataset. Since there's no speaker conditioning, the speaker is random at inference. This …

Nov 4, 2025 · Echolancer: Yet another Text-to-Speech (TTS) model Here I introduce a TTS model I managed to somehow pretrain on a single GPU.

Echolancer-v0.1-zs This is a TTS model trained on approximately ~5-7k hours of private labeled data, finetuned from the base model; it's conditioned on SpeechBrain ECAPA embeddings.

Echolancer A text-to-speech model trained on concatenated text-audio tokens using a modern LLM-style decoder-only approach. Features a 50 tok/s codebook for efficient audio language modeling.

It's a text to speech model. Contribute to ZDisket/Echolancer development by creating an account on GitHub.

echolancer-stage2-zs ... This is a 550M param version of this model. For more information including a Colab notebook, see the repository.

It's a text to speech model. Contribute to ZDisket/Echolancer development by creating an account on GitHub.

echolancer-stage2-base ... Echolancer Stage 2 Base This is a TTS model pretrained on the pre-tokenized Emilia dataset. Since there's no speaker conditioning, the speaker is random at inference. …