home.social

#texttospeech — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #texttospeech, aggregated by home.social.

fetched live
  1. Some language learning apps gamify word recognition, but it isn't enough.

    That's why Lexolotl flashcard drills include Usage Examples — Apple Intelligence and Text to Speech let you see and hear the word you're learning, reinforcing the language.

    Learn more: mathaesthetics.com/wp/see-the-

    #languagelearning #macOS #iPhone #iPad #flashcard #langauge #app #learning #education #sentences #texttospeech #AppleIntelligence #swift #swiftui #spacedrepetition #langaugestudy #student #langaugepractice

  2. Some language learning apps gamify word recognition, but it isn't enough.

    That's why Lexolotl flashcard drills include Usage Examples — Apple Intelligence and Text to Speech let you see and hear the word you're learning, reinforcing the language.

    Learn more: mathaesthetics.com/wp/see-the-

    #languagelearning #macOS #iPhone #iPad #flashcard #langauge #app #learning #education #sentences #texttospeech #AppleIntelligence #swift #swiftui #spacedrepetition #langaugestudy #student #langaugepractice

  3. 😆 Oh, look! A text-to-speech system for #Sanskrit, because who doesn't want to hear ancient verses spoken in robot voice? 🤖🎙️ Just paste your favorite Sanskrit verse and wait a lifetime (10-60 seconds) for the magic to happen! If this doesn't load, try the backup demo – because redundancy is #innovation, right? 😂
    prathosh.in/vagdhenu/ #texttospeech #technology #humor #robotvoice #HackerNews #ngated

  4. 😆 Oh, look! A text-to-speech system for #Sanskrit, because who doesn't want to hear ancient verses spoken in robot voice? 🤖🎙️ Just paste your favorite Sanskrit verse and wait a lifetime (10-60 seconds) for the magic to happen! If this doesn't load, try the backup demo – because redundancy is #innovation, right? 😂
    prathosh.in/vagdhenu/ #texttospeech #technology #humor #robotvoice #HackerNews #ngated

  5. 🎤 dbccccccc/ttsfm

    Mimics OpenAI's TTS API with 11 voices and multiple audio formats, offering REST endpoints, a Python SDK and web interface

    ⭐ Stars: 727
    📅 Last Update: Jul 15, 2026

    github.com/dbccccccc/ttsfm

    #selfhosted #homelab #selfhost #selfhosting #opensource #texttospeech #openaicompatible

  6. Has anyone run into this?
    The built-in macOS text-to-speech engine isn't respecting the speech rate I've set. No matter what I choose, it keeps speaking at what seems like the default speed instead of my preferred rate.
    Has anyone found a fix or workaround for this? Thanks!
    #macOS #Accessibility #VoiceOver #TextToSpeech #TTS #AssistiveTechnology #AppleAccessibility #Blind

  7. Has anyone run into this?
    The built-in macOS text-to-speech engine isn't respecting the speech rate I've set. No matter what I choose, it keeps speaking at what seems like the default speed instead of my preferred rate.
    Has anyone found a fix or workaround for this? Thanks!
    #macOS #Accessibility #VoiceOver #TextToSpeech #TTS #AssistiveTechnology #AppleAccessibility #Blind

  8. Inspired by "Text to Speech on ESP32 - Wit.ai & OpenAI TTS" youtube.com/watch?v=dNadDhVf-Kg (#DroneBotWorkshop ), I compared three self-hosted text-to-speech systems--Piper, Kokoro, and Qwen3-TTS.

    All performed well, but Piper's modest resource requirements make it my likely choice for an entirely in-house ESP32 TTS service. I have included the audio files, too.

    salemdata.net/johnpress/?p=1076

    #TextToSpeech #TTS #ESP32 #OpenSource #SelfHosted #PiperTTS

  9. Successful 27 day ++ (with ) project integrated with my written, debugged, and full functionality testing with one to two daily sessions on the free web browser interface.

    I had to remind/request Claude use and and some but all other implementation decisions were as I would choose.

  10. Voicebox is a free and open-source AI voice studio that runs entirely on your computer.

    It lets you clone voices, generate speech, transcribe audio with Whisper, and use voice dictation without sending recordings to the cloud. It also supports multiple TTS engines and MCP integration for AI assistants.

    More details: digitalescapetools.com/tools/t

    #OpenSource #AI #Privacy #SelfHosted #Linux #Windows #macOS #SpeechToText #TextToSpeech

  11. Voicebox is a free and open-source AI voice studio that runs entirely on your computer.

    It lets you clone voices, generate speech, transcribe audio with Whisper, and use voice dictation without sending recordings to the cloud. It also supports multiple TTS engines and MCP integration for AI assistants.

    More details: digitalescapetools.com/tools/t

    #OpenSource #AI #Privacy #SelfHosted #Linux #Windows #macOS #SpeechToText #TextToSpeech

  12. Can you tell this voice is AI? It sounds very human to me.

    Free tool used to generate audio: #Omnivoice on #Linux

    This is the reading of Part II to the poem:
    Muspilli

    meaning "World's End"

    (from the year 870 AD, originally written in Old German by anonymous)

    Old High German is no longer used today in normal communications, but #AI could still translate it.

    john1126.com/537

    #German #OldGerman #poetry #poem #AIaudio #TextToSpeech #prophecy

  13. Can you tell this voice is AI? It sounds very human to me.

    Free tool used to generate audio: #Omnivoice on #Linux

    This is the reading of Part II to the poem:
    Muspilli

    meaning "World's End"

    (from the year 870 AD, originally written in Old German by anonymous)

    Old High German is no longer used today in normal communications, but #AI could still translate it.

    john1126.com/537

    #German #OldGerman #poetry #poem #AIaudio #TextToSpeech #prophecy

  14. 🔊 travisvn/openai-edge-tts

    Free, high-quality text-to-speech API endpoint to replace OpenAI, Azure, or ElevenLabs

    Provides a free text-to-speech API endpoint as an alternative to paid services like OpenAI or ElevenLabs

    ⭐ Stars: 1928
    📅 Last Update: Jun 12, 2026

    github.com/travisvn/openai-edg

    #selfhosted #homelab #selfhost #selfhosting #opensource #texttospeech #api

  15. Наш синтез для экранных читалок (SAPI5) для 20 языков России стал лучше

    Мы не так давно опубликовали SAPI5-обёртку для нашего синтеза на 20 языков России и СНГ. В этот раз опять немного сошлись звёзды и мы уже публикуем улучшение наших читалок. Чтобы не растекаться мыслью по древу и не повторяться, вот краткий список улучшений (полную подводку можно прочитать в прошлой статье ): Покажите список улучшений

    habr.com/ru/articles/1043466/

    #silero #синтез_речи #tts #texttospeech #нейросети #озвучка #русский_язык #языки_россии #sapi #балаболка

  16. Success!! I've completed a first reimplementation of Dr. Sbaitso voice synthesis in Godot!

    Try it out at Itchio: eibriel.itch.io/scp-079-voice

    Ive configure the accessibility settings so the app properly describes the input fields and buttons, but for some reason is not working for me (tested on Linux with Orca). Let me know if it works for you!

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079 #SCP #Godot

  17. Some improvements to the concatenation, prosody is still missing.

    Here is a well known phrase by SCP 079.

    The audio contains the same phrase first performed by Dr. Sbaitso TTS and the by Godot reimplementation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079 #SCP #Godot

  18. Dr. Sbaitso compared to my reimplementation in Godot (Sbaitso first) :computer_explorer: :pc_color:

    Implemented: basic waveform concatenation
    Missing: Interpolation, pitch control, prosody, text to phonemes

    Im very happy with the progress, will be great to be able to run the voice without needing emulation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079

  19. What I've learned so far while reverse engineering Dr Sbaitso's voice:
    - Reverse engineering is hard

    Also, the voice was made by very clever people. It's optimized to sound as good as possible, while consuming very few resources.

    Progress after 5 days: 10%

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech

  20. Anyone have a good quality text-to-speech app that is easy to use in a browser? MacOSX has a free one built-in via accessibility, but the voice quality is low. And abrasive. I was hoping for a FireFox add-in that might be free or inexpensive. Can't find anything. #TextToSpeech #Speech #reading