71–78 of 78 posts
Earlier quoted context omitted.
A 25MB TTS model: https://github.com/kittenml/kittentts
Nice, I’ll have to try it out. They should really make a uv-installable CLI tool like pocket-TTS did. People underestimate just how much more immediately usable something becomes when you can simply get something by doing “uv tool install …”
I just open sourced a REST API and framework that you can point any of your projects to such as OpenClaw so you can do TTS and SST using your own hardware.
It's specially focused on Mac M-class chips to utilize MLX:
https://github.com/Sogni-AI/sogni-voice
All free and open source.
Internally it uses Parakeet, Kokoro TTS, Qwen3 TTS (with voice cloning support!) Also supports creating your own API key to lock your API to your own apps.
This is not strictly speech-to-speech, but I quite like it when working with Claude Code or other CLI Agents: STT: Handy [1] (open-source), with Parakeet V3 - stunningly fast, near-instant transcription. The slight accuracy drop relative to bigger models is immaterial when you're talking to an AI. I always ask it to restate back to me what it understood, and it gives back a nicely structured version -- this helps con…
Earlier quoted context omitted.
A 25MB TTS model: https://github.com/kittenml/kittentts
Nice, I’ll have to try it out. They should really make a uv-installable CLI tool like pocket-TTS did. People underestimate just how much more immediately usable something becomes when you can simply get something by doing “uv tool install …”
This is not strictly speech-to-speech, but I quite like it when working with Claude Code or other CLI Agents: STT: Handy [1] (open-source), with Parakeet V3 - stunningly fast, near-instant transcription. The slight accuracy drop relative to bigger models is immaterial when you're talking to an AI. I always ask it to restate back to me what it understood, and it gives back a nicely structured version -- this helps con…
I've been dabbling with STT quite a bit and built my own tool using Deepgram. But just tried Handy and it's SO FREAKING FAST! Love it.
This is not strictly speech-to-speech, but I quite like it when working with Claude Code or other CLI Agents: STT: Handy [1] (open-source), with Parakeet V3 - stunningly fast, near-instant transcription. The slight accuracy drop relative to bigger models is immaterial when you're talking to an AI. I always ask it to restate back to me what it understood, and it gives back a nicely structured version -- this helps con…
I've been dabbling with STT quite a bit and built my own tool using Deepgram. But just tried Handy and it's SO FREAKING FAST! Love it.
This is not strictly speech-to-speech, but I quite like it when working with Claude Code or other CLI Agents: STT: Handy [1] (open-source), with Parakeet V3 - stunningly fast, near-instant transcription. The slight accuracy drop relative to bigger models is immaterial when you're talking to an AI. I always ask it to restate back to me what it understood, and it gives back a nicely structured version -- this helps con…
I've been dabbling with STT quite a bit and built my own tool using Deepgram. But just tried Handy and it's SO FREAKING FAST! Love it.
https://github.com/kitlangton/Hex
Also the transcriptions with hex don't seem to suffer from some of the issues with Handy, such as stutter.
Earlier quoted context omitted.
I've been dabbling with STT quite a bit and built my own tool using Deepgram. But just tried Handy and it's SO FREAKING FAST! Love it.
For local speech-to-text, Whisper remains the gold standard - you can run it locally with good accuracy across languages. For speech-to-speech, you'd typically chain Whisper with a local TTS model like Coqui TTS or use something like Tortoise TTS for higher quality but slower processing. The key is balancing accuracy, speed, and resource usage based on your specific use case. If you're doing content creation workflow…
I built MumbleFlow to address exactly this — whisper.cpp for STT plus llama.cpp for smart text cleanup, all running on-device. Metal/CUDA accelerated, sub-second latency on Apple Silicon. Global hotkey works in any app.
$5 one-time, no cloud, no subscription. https://mumble.helix-co.com