PulseAugur
EN
LIVE 18:21:36
ENTITY Pocket TTS

Pocket TTS

PulseAugur coverage of Pocket TTS — every cluster mentioning Pocket TTS across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
10
16 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
0
1 over 90d
TIER MIX · 90D
TOPICS
TIMELINE
  1. 2026-07-06 product_launch Kyutai released Pocket TTS, a new text-to-speech model capable of voice cloning from short audio samples. source
  2. 2026-07-06 product_launch Kyutai released Pocket TTS, a new CPU-based text-to-speech model capable of zero-shot voice cloning. source
SENTIMENT · 30D

5 day(s) with sentiment data

RECENT · PAGE 1/1 · 16 TOTAL
  1. TOOL · CL_348110 ·

    Underdog Woof TTS model released, runs on CPU

    ConwayResearch has released Underdog Woof, a compact English text-to-speech model that is significantly smaller and faster than comparable models. It boasts a word error rate of 1.42% on specific test cases and can run …

  2. TOOL · CL_342790 ·

    Hugging Face launches Phonon TTS for on-device, high-quality speech

    Hugging Face has released Phonon, a small, on-device text-to-speech model designed for privacy and offline use. The model, available in two sizes, supports multiple languages and handles complex inputs like phone number…

  3. TOOL · CL_335478 ·

    Silencio-2 TTS model released with emotion and sound tags

    A new open-weight Text-to-Speech model named Silencio-2 has been released, built upon Kyutai's Pocket TTS. This model, with 18.2 million parameters, can incorporate emotion and sound tags directly within the text to inf…

  4. TOOL · CL_332308 ·

    Anthropic SDKs and Claude Code see major updates, Ollama adds new models

    Anthropic has released several updates across its SDKs and tools, including new features for its Python SDK and Claude Code. The Python SDK now supports more detailed analytics, error handling, and integration with clou…

  5. TOOL · CL_316407 ·

    Gradium open-sources Phonon on-device TTS models

    Gradium has released Phonon, a family of on-device text-to-speech models available in 31M and 40M parameter sizes. The English-only Phonon 31m model, licensed under Apache 2.0, is a compact 64.5 MB and can generate spee…

  6. TOOL · CL_313840 ·

    Hugging Face Transformers v5.21.0 adds new models, including document understanding and TTS capabilities

    Hugging Face's Transformers library has released version 5.21.0, introducing several new models and updates. Notable additions include MiniCPM-OCR for document understanding, Flint, a mixture-of-experts language model w…

  7. TOOL · CL_311178 ·

    Locally Uncensored adds live voice assistant for local LLMs

    The open-source desktop application Locally Uncensored has introduced a new live voice assistant feature, allowing users to interact with local LLMs through speech. This beta functionality, currently English-only, integ…

  8. TOOL · CL_311113 ·

    Pocket TTS achieves voice cloning with 1.9M parameters

    Pocket TTS, a text-to-speech system capable of voice cloning, has been released with a significantly reduced size of just 1.9 million parameters. This development makes the technology more accessible for local deploymen…

  9. TOOL · CL_306962 ·

    AI video studio automates content creation, slashing costs to zero

    A developer has created an automated video production studio powered by Claude Code, capable of generating up to 40 videos in ten days. This studio researches topics, scripts content, clones the creator's voice using op…

  10. TOOL · CL_248289 ·

    Local GPT Live clone runs on RTX 3060 using Qwen3.5 9B model

    A user has successfully created a local clone of the GPT Live voice assistant, capable of running on a consumer-grade NVIDIA GeForce RTX 3060 graphics card with 12GB of VRAM. The setup utilizes the Qwen3.5 9B model for …

  11. RESEARCH · CL_199292 ·

    CPU Voice Cloning Benchmark: Pocket TTS, Kokoro, Audio8, XTTS v2 Compared

    A practical benchmark evaluated four voice cloning models (Pocket TTS, Kokoro, Audio88 & Yassin, and XTTS v2) on CPU performance. The evaluation focused on speaker similarity, naturalness, intelligibility, and latency, …

  12. TOOL · CL_196480 ·

    Llama.cpp adds on-device text-to-speech with Pocket-TTS integration

    The Llama.cpp project has integrated Pocket-TTS, enabling on-device text-to-speech generation without requiring cloud services. This integration allows for local voice synthesis directly from repositories that already s…

  13. TOOL · CL_127886 ·

    CPU TTS benchmark: Pocket TTS shows flat RTF, UTMOS struggles with naturalness

    A benchmark comparing four CPU-based text-to-speech (TTS) models—Kokoro, Supertonic, Inflect-Nano, and Pocket TTS—reveals distinct performance characteristics. Pocket TTS, utilizing a streaming language model architectu…

  14. TOOL · CL_127764 ·

    Kyutai's Pocket TTS offers CPU-based voice cloning from 5s audio

    Kyutai has released Pocket TTS, a ~100M parameter streaming language model that generates audio tokens autoregressively. This model is notable for its ability to perform zero-shot voice cloning from just 5 seconds of au…

  15. TOOL · CL_116438 ·

    User seeks help implementing Calm TTS paper, facing voice cloning issues

    A user is seeking assistance with implementing the Calm text-to-speech model described in a research paper. They have encountered difficulties in replicating the model's performance, experiencing issues with generating …

  16. TOOL · CL_319073 ·

    Phonon-31m: On-device English TTS model released

    The gradium/phonon-31m-en model is a high-quality, on-device text-to-speech system capable of generating natural 24 kHz English speech. It is small enough to run in a browser, on a phone, or a laptop CPU, and streams au…