←Search results

Search “Speech”

By relevance · Total 1347 results Clear search

Monday

Saturday

Friday

Thursday

  2. Simon Willison

    Simon Willison Builds a Bring-Your-Own-Key Voice Playground with Gemini 3.8 TTS

    Google released two text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, offering more than 2000 voices and support for creating custom voices from 30-second audio samples. Leveraging the Gemini API's open CORS policy, Simon Willison quickly built a bring-your-own-key Playground with GPT-6 Astra and demonstrated speech generation for multi-character dialogue. In his test, generating 1 minute 18 seconds of audio with Gemini 3.8 Flash TTS took about 20 seconds and cost 2.74 cents.

    Google released two text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, offering more than 2000 voices and support for creating custom voices from 30-second audio samples. Leveraging the Gemini API's open CORS policy, Simon Willison quickly built a bring-your-own-key Playground with GPT-6 Astra and demonstrated speech generation for multi-character dialogue. In his test, generating 1 minute 18 seconds of audio with Gemini 3.8 Flash TTS took about 20 seconds and cost 2.74 c

    Matched fieldsTitle、Summary、Body

    #newsletter#Product updates#Speech#Google

Wednesday

Tuesday

  2. SSPAI

    Using a 60-yuan Xiaomi Bluetooth Remote 2 Pro as a Handheld Voice Controller for AI Programming

    The SSPAI author neyham used a roughly 50–60 yuan Xiaomi TV Bluetooth Voice Remote 2 Pro (model RC003) together with the open-source tool SayAll to turn the remote into a handheld controller for AI programming: hold the voice button to dictate a prompt, release to send it to the screen, and use the directional buttons to switch terminal tabs and workspaces. SayAll generates a virtual microphone, MiRemoteV 2ch, which is used with the WeChat Input Method's hold-to-talk feature; configuration paths are provided for both macOS and Windows. The article also offers troubleshooting methods for issues such as SayAll getting stuck during onboarding and the WeChat Input Method being unable to register a standalone Fn key.

    The SSPAI author neyham used a roughly 50–60 yuan Xiaomi TV Bluetooth Voice Remote 2 Pro (model RC003) together with the open-source tool SayAll to turn the remote into a handheld controller for AI programming: hold the voice button to dictate a prompt, release to send it to the screen, and use the directional buttons to switch terminal tabs and workspaces. SayAll generates a virtual microphone, MiRemoteV 2ch, which is used with the WeChat Input Method's hold-to-talk feature; configuration paths

    Matched fieldsTitle、Summary、Body

    #hot-signal#Tutorials / practice#Speech#English text is being prepared.

Monday

Saturday