Changelog

September 16, 2026

• New pageAssemblyAI: Published the open-source alternatives to AssemblyAI page.
• AddedBolna: An MIT voice-agent platform that defines an agent in a JSON file and orchestrates speech to text, a language model and text to speech over websockets, with Twilio and Plivo for phone calls, whose maintainers say they are looking for help.
• AddedBuzz: A desktop app under MIT that transcribes and translates audio and video files, YouTube links and a live microphone offline with Whisper, with speaker identification and SRT, VTT and TXT export.
• AddedChatterbox: A family of text-to-speech models from Resemble AI under MIT, with zero-shot voice cloning from a reference clip and a multilingual model covering 23 languages.
• New pageDeepgram: Published the open-source alternatives to Deepgram page.
• New pageElevenLabs: Published the open-source alternatives to ElevenLabs page.
• New pageElevenLabs Agents: Published the open-source alternatives to ElevenLabs Agents page.
• AddedF5-TTS: A research text-to-speech model with zero-shot voice cloning whose code is MIT but whose pretrained weights are non-commercial, because of the dataset they were trained on.
• New pageFireflies.ai: Published the open-source alternatives to Fireflies.ai page.
• AddedFish Speech: A multilingual text-to-speech system with voice cloning from a 10 to 30 second clip and inline emotion tags, released with its weights under a research licence that requires a separate agreement for commercial use.
• AddedHandy: A free, offline push-to-talk dictation app for macOS, Windows and Linux that runs Whisper or NVIDIA Parakeet on your own machine and pastes the text at your cursor, under MIT.
• AddedKokoro FastAPI: A Docker image that serves the 82-million-parameter Kokoro model through an OpenAI-compatible speech endpoint, with streaming, voice mixing and nine languages, all under Apache-2.0.
• AddedLiveKit Agents: An Apache-2.0 framework for real-time voice agents that connects any speech, language and voice provider, with semantic turn detection, native MCP tool support, a test framework, and an open-source media and SIP stack it can run on entirely.
• AddedMeetily: A meeting assistant under MIT that records your microphone and system audio together, transcribes live on your machine with Whisper or Parakeet, and summarises with a language model you choose.
• AddedMoonshine: An on-device speech toolkit under MIT built for live streaming, with speech-to-text models trained from scratch in sizes down to 1 MB, one library across Python, the browser, phones and desktops.
• AddedOpenWhispr: A dictation and meeting-notes app under MIT that runs Whisper or Parakeet locally or cloud models with your own key, detects Zoom, Teams and FaceTime calls, and labels speakers on device.
• New pageOtter.ai: Published the open-source alternatives to Otter.ai page.
• AddedParakeet (NeMo Speech): Added Parakeet (NeMo Speech): NVIDIA's speech models and toolkit: Apache-2.0 code, and the Parakeet TDT 0.6B v3 model under CC-BY-4.0 with 25 European languages, automatic language detection, punctuation and word timestamps.
• AddedPipecat: A Python framework under BSD-2-Clause, maintained by Daily, for real-time voice and multimodal agents, with the widest provider list on this site and telephony serialisers for Twilio, Telnyx, Plivo, Vonage, Exotel and Genesys.
• AddedPiper: A fast, local neural text-to-speech engine maintained by the Open Home Foundation, used by Home Assistant and the NVDA screen reader, under GPL-3.0.
• New pageRetell AI: Published the open-source alternatives to Retell AI page.
• Addedsherpa-onnx: A runtime under Apache-2.0 from the next-generation Kaldi team that runs speech to text, text to speech, speaker diarization and voice activity detection locally on CPUs, NPUs and phones, with no internet connection.
• AddedSpeaches: An OpenAI-compatible server under MIT for streaming transcription, translation and text to speech, loading Whisper, Kokoro and Piper models on demand, described by its maintainers as Ollama for speech models.
• New pageSuperwhisper: Published the open-source alternatives to Superwhisper page.
• AddedTEN Framework: A real-time conversational AI framework from Agora with a visual designer, a SIP extension and turn detection, released under Apache-2.0 plus conditions that forbid competing deployments, which makes it source available rather than open source.
• New pageVapi: Published the open-source alternatives to Vapi page.
• AddedVibe: An offline transcription app under MIT that records system audio and the microphone, supports Whisper, Parakeet and Nemotron models, labels speakers, and exports SRT, VTT, TXT, HTML, PDF, JSON and DOCX.
• AddedVoiceInk: A macOS dictation app under GPL-3.0 whose README names Superwhisper and Wispr Flow as the tools it replaces, with local models, per-app modes, a personal dictionary and an AI assistant mode.
• AddedVosk: An offline speech recognition toolkit under Apache-2.0 with streaming, models of about 50 MB, 20+ languages, a reconfigurable vocabulary and speaker identification, from small boards to clusters.
• AddedWhisper: OpenAI's general-purpose speech recognition model, released with code and weights under MIT, in six sizes from 39 million to 1.55 billion parameters, with multilingual transcription, translation to English and language detection.
• Addedwhisper.cpp: A dependency-free C and C++ port of Whisper under MIT that runs on CPUs, Apple Silicon and phones, with quantised models, an HTTP server and bindings for a dozen languages.
• AddedWhispering: A speech-to-text app inside the Epicenter monorepo under AGPL-3.0 that records, transcribes with a provider you choose, cloud or local, optionally polishes the text, and pastes it at the cursor.
• AddedWhisperX: Batched Whisper transcription under BSD-2-Clause with word-level timestamps from forced alignment and speaker labels from pyannote, the closest open-source match to a hosted transcription API's output.
• New pageWispr Flow: Published the open-source alternatives to Wispr Flow page.