Skip to main content
← Back to news

Meet Dessa, the speech model trained from scratch on human conversation

Model releases
Source:Block (admin inbox)
Block introduces Dessa, a speech model trained from scratch on human conversation. The company already uses it for phone support: a case study in how natural a TTS/STT is when not fine-tuned on a large existing model.
Read original article

Related articles

La voce locale: da Whisper al text-to-speech

Come costruire una pipeline di voce completamente locale: trascrizione con Whisper, sintesi con Piper o Kokoro-82M, requisiti hardware e casi d'uso pratici.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

🎙️

speech-swift (Kyutai STT)

Software

A Swift/MLX runtime for Kyutai's streaming speech recognition on Apple Silicon. The reference checkpoint is the STT-1B (English and French) in INT8/FP16, with a causal Mimi encoder (32 audio codes every 80ms). Supports INT4/INT8 exports. CC-BY-4.0 weights license.

🗣️

Piper TTS

Inference

Sintesi vocale in locale a bassa latenza basata su ONNX: genera parlato naturale da testo in tempo quasi reale, anche su CPU. Multilingue (italiano incluso) e facile da integrare nei pipeline: download del modello, una riga di comando. MIT.

🎵

Kokoro-82M

Models

82-million-parameter speech synthesis model on a VITS architecture, Apache-2.0 for the weights, with voices in dozens of languages and surprisingly high quality for its size. Runs efficiently on CPU alone.

🗣️

NVIDIA MagpieTTS Multilingual 357M

Models

Modello di sintesi vocale multilingue di NVIDIA: 357M parametri, 12 lingue (italiano e francese inclusi), architettura encoder-decoder transformer. Compatto e pensato per esecuzione in locale a bassa latenza; pesi disponibili su Hugging Face.

Browse all resources