--- id: "/generative-media/voice-speech/" title: "voice & speech: 49 curated resources" url: "https://skillissue.dev/generative-media/voice-speech/" --- # voice & speech: 49 curated resources voice & speech [Beginner](/generative-media/beginner/index.md) [Intermediate](/generative-media/intermediate/index.md) [Advanced](/generative-media/advanced/index.md) [Expert](/generative-media/expert/index.md) 49 resources · page 1 of 2 - ### [AssemblyAI Universal-3.5 Pro](/frontier/model-releases/assemblyai-universal-3-5-pro/index.md) by [AssemblyAI](https://assemblyai.com/) AssemblyAI documentation for Universal-3.5 Pro: pre-recorded speech-to-text in 18 languages with code switching and prompting. entity model US en - ### [Breeze TTS 2](/frontier/model-releases/breeze-tts-2-developer-not-exposed/index.md) by [Breeze Blue](https://breezeblue.ai/) BreezeBlue announcement of Breeze TTS 2, an open-weight English and Chinese text-to-speech model with voice design, cloning and streaming output. entity model unverified en - ### [cohere-transcribe-03-2026](/frontier/model-releases/cohere-transcribe-2b/index.md) by [Cohere Labs](https://huggingface.co/CohereLabs) Hugging Face model card for CohereLabs/cohere-transcribe-03-2026, a 2B-parameter open speech recognition model for 14 languages. entity model Canada mul - ### [CosyVoice](/frontier/model-releases/cosyvoice/index.md) by [QwenAudio](https://www.funasr.com) QwenAudio CosyVoice GitHub repo: multilingual voice generation model with inference, training and deployment. entity repo China zh - ### [faster-whisper (Systran)](/frontier/model-releases/faster-whisper-systran/index.md) by [SYSTRAN](https://www.systransoft.com/) SYSTRAN faster-whisper GitHub repo: Whisper reimplementation on CTranslate2 for faster transcription. entity repo EU-DE en - ### [Fun-Realtime-ASR-preview](/frontier/model-releases/fun-realtime-asr-preview/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Artificial Analysis speech-to-text page for Alibaba, covering Fun-Realtime-ASR-preview: word error rate, speed and price compared with other models. entity model China en - ### [Gemini 2.5 Pro](/frontier/model-releases/gemini-2-5-pro/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Artificial Analysis speech-to-text page for Google, covering Gemini 2.5 Pro: word error rate, speed and price compared with other models. entity model US / UK en - ### [GigaAM (Sber)](/frontier/model-releases/gigaam-sber/index.md) by [Salute Developers](https://github.com/salute-developers) Sber GigaAM GitHub repo: foundational models for Russian speech recognition. entity repo RU en - ### [GigaAM-v3: открытая SOTA-модель распознавания речи на русском языке](/frontier/model-releases/gigaam-v3-sber/index.md) by [Sber](https://www.sber.ru/) Sber developers article on GigaAM-v3, an open MIT-licensed Russian speech recognition model released on GitHub and Hugging Face. entity model Russia ru - ### [Gladia Solaria-3](/frontier/model-releases/gladia-solaria-3/index.md) by [Gladia](https://gladia.io/) Gladia page for Solaria-3, its pre-recorded speech-to-text model for English, French, German, Spanish and Italian. entity model France en - ### [GPT Transcribe](/frontier/model-releases/gpt-transcribe/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Artificial Analysis speech-to-text page for OpenAI, covering GPT Transcribe: word error rate, speed and price compared with other models. entity model US en - ### [Grok Voice Transcribe 2.0](/frontier/model-releases/grok-voice-transcribe-2-0/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Artificial Analysis speech-to-text page for SpaceXAI, covering Grok Voice Transcribe 2.0: word error rate, speed and price compared with other models. entity model US en - ### [granite-4.0-1b-speech](/frontier/model-releases/ibm-granite-4-0-1b-speech/index.md) by [IBM Granite](https://huggingface.co/ibm-granite) Hugging Face model card for ibm-granite/granite-4.0-1b-speech, IBM's compact speech recognition and translation model. entity model US mul - ### [IndicVoices](/frontier/model-releases/indicvoices/index.md) by [AI4Bhārat](https://ai4bharat.iitm.ac.in) IndicVoices GitHub repo (AI4Bharat): 12,000-hour dataset of natural speech in Indian languages. entity repo India en - ### [Kokoro TTS](/frontier/model-releases/kokoro-tts/index.md) by [Hexgrad](https://huggingface.co/hexgrad) Hugging Face model card for hexgrad/Kokoro-82M, an 82M-parameter open text-to-speech model, with weights, usage and license details. entity model US en - ### [Kyutai (Moshi)](/frontier/model-releases/kyutai-moshi/index.md) by [Kyutai](https://kyutai.org/) Kyutai: French open-science AI lab releasing audio models such as Moshi, Hibiki and Unmute, with papers. entity lab EU-FR en - ### [MAI-Transcribe-1.5](/frontier/model-releases/mai-transcribe-1-5/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Artificial Analysis speech-to-text page for Microsoft, covering MAI-Transcribe-1.5: word error rate, speed and price compared with other models. entity model US en - ### [MedASR (Google)](/frontier/model-releases/medasr-google/index.md) by [Google Research](https://research.google/) Google Research post on MedGemma 1.5 medical image interpretation and MedASR medical speech-to-text. entity model US en - ### [Mozilla Common Voice](/frontier/model-releases/mozilla-common-voice/index.md) by [Common Voice](https://commonvoice.mozilla.org) Mozilla Common Voice GitHub repo: platform code for the crowdsourced multilingual voice dataset. entity repo Global mul - ### [NVIDIA Canary-Qwen-2.5B](/frontier/model-releases/nvidia-canary-qwen-2-5b/index.md) by [NVIDIA](https://huggingface.co/nvidia) Hugging Face model card for nvidia/canary-qwen-2.5b, NVIDIA's 2.5B speech recognition model combining Canary and Qwen, with weights, usage and license details. entity model US en - ### [NVIDIA Parakeet TDT 0.6B v3](/frontier/model-releases/nvidia-parakeet-tdt-0-6b-v3/index.md) by [NVIDIA](https://huggingface.co/nvidia) Hugging Face model card for nvidia/parakeet-tdt-0.6b-v3, NVIDIA's 0.6B Parakeet multilingual speech recognition model, with weights, usage and license details. entity model US mul - ### [OpenMOSS (Fudan)](/frontier/model-releases/openmoss-fudan/index.md) by [OpenMOSS (SII)](https://openmoss.ai/) OpenMOSS GitHub organisation (Shanghai Innovation Institute and Fudan): MOSS, MOSS-TTSD and SpeechGPT code. entity lab CN en - ### [DeepFilterNet](/frontier/model-releases/podcast-speech-denoising-deepfilternet-usage-verified-free-code-documented-cli-a/index.md) by [Hendrik Schröter](https://github.com/Rikorose) DeepFilterNet GitHub repo: deep filtering noise suppression for speech audio. entity repo US en - ### [pyannote Hugging Face organization](/frontier/model-releases/pyannote-diarization/index.md) by [pyannote](https://huggingface.co/pyannote) pyannote Hugging Face organisation: speaker diarization and voice activity detection models. entity lab EU-FR en - ### [Resonant-1](/frontier/model-releases/resonant-1/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Artificial Analysis speech-to-text page for Reson8, covering Resonant-1: word error rate, speed and price compared with other models. entity model International; domicile unverified en - ### [Scribe v2](/frontier/model-releases/scribe-v2/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Artificial Analysis speech-to-text page for ElevenLabs, covering Scribe v2: word error rate, speed and price compared with other models. entity model UK / US en - ### [Silero models](/frontier/model-releases/silero-models/index.md) by [Alexander Veysov](https://github.com/snakers4) Silero models GitHub repo: pretrained speech-to-text and text-to-speech models. entity repo RU en - ### [Silero VAD](/frontier/model-releases/silero-vad/index.md) by [Alexander Veysov](https://github.com/snakers4) Silero VAD GitHub repo: pretrained voice activity detection model for streaming audio. entity repo Russia-origin; international en - ### [smallest-python-sdk](/frontier/model-releases/smallest-ai-official-python-sdk-and-examples/index.md) by [Smallest AI](https://smallest.ai/) Smallest AI Python SDK GitHub repo: official client for the Smallest AI speech API. entity repo United States en - ### [Smallest AI Pulse](/frontier/model-releases/smallest-ai-pulse/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Artificial Analysis speech-to-text page for Smallest.ai, covering Smallest AI Pulse: word error rate, speed and price compared with other models. entity model US / India en - ### [Smallest AI Pulse Pro](/frontier/model-releases/smallest-ai-pulse-pro/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Artificial Analysis speech-to-text page for Smallest.ai, covering Smallest AI Pulse Pro: word error rate, speed and price compared with other models. entity model US / India en - ### [Solaria-3](/frontier/model-releases/solaria-3/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Artificial Analysis speech-to-text page for Gladia, covering Solaria-3: word error rate, speed and price compared with other models. entity model France en [Next page](/generative-media/voice-speech/page/2/index.md) [Plain-text Markdown copy](/generative-media/voice-speech/index.md)