voice
์ด 9๊ฐ์ ์ํค ยท 1 / 1 ํ์ด์ง ๐ก RSS ๐ธ๏ธ ๊ทธ๋ํ
- [Voice AI] Speech-to-Speech: OpenAI Realtime, Gemini Live, Moshi#s2s #realtime-api #gpt-4o #gemini-live #moshi #voice-llm
- [Voice AI] STT ๋ชจ๋ธ: Whisper, Deepgram, AssemblyAI, CLOVA#stt #asr #voice #whisper #deepgram #assemblyai
- [Voice AI] STT ์คํธ๋ฆฌ๋ฐ: partial vs final, endpointing, gRPC/WS#stt #streaming #asr #partial #final #endpointing
- [Voice AI] TTS ๋ชจ๋ธ: ElevenLabs, Cartesia, Edge TTS, ํ๊ตญ์ด#tts #voice-synthesis #neural-tts #voice-cloning #korean
- [Voice AI] TTS ์คํธ๋ฆฌ๋ฐ + SSML: TTFB, sentence aggregation, ์ฒญํน#tts #streaming #ssml #ttfb #prosody
- [Voice AI] Turn Detection + Barge-in + AEC: ์์ฐ์ค๋ฌ์ด ๋ํ#turn-detection #barge-in #aec #duplex #voice-agent
- [Voice AI] VAD: Silero, ์๋์ง ๊ธฐ๋ฐ, endpointing ์๊ณ๊ฐ#vad #silero #voice-activity #endpointing #audio
- [Voice] Neural TTS ๋ด๋ถ: Tacotron, FastSpeech, VITS, HiFi-GAN#tts #neural-tts #vits #hifi-gan #transformer
- [Voice] Whisper ๋ด๋ถ: encoder-decoder, log-mel, tokenizer#whisper #stt #asr #transformer #encoder-decoder