--- id: "/tags/voice-speech/" title: "Voice Speech" creator: null creator_url: null creator_x: null url: "https://skillissue.dev/tags/voice-speech/" level: null level_max: null category: null subcategory: null region: null license: null license_scope: null access: null models: null source_date: null date_added: null resource_kind: null verification_basis: null access_evidence: null domain_top: null domain_sub: null last_verified: null --- # Voice Speech [Beginner](/levels/beginner/index.md) [Intermediate](/levels/intermediate/index.md) [Advanced](/levels/advanced/index.md) [Expert](/levels/expert/index.md) 49 resources · page 1 of 2 - ### [AssemblyAI Universal-3.5 Pro](/frontier/model-releases/assemblyai-universal-3-5-pro/index.md) Creator not supplied; see original source. AssemblyAI documentation for Universal-3.5 Pro: pre-recorded speech-to-text in 18 languages with code switching and prompting. Not applicable (entity) · unknown · unknown resource · en - ### [Breeze TTS 2](/frontier/model-releases/breeze-tts-2-developer-not-exposed/index.md) Creator not supplied; see original source. BreezeBlue announcement of Breeze TTS 2, an open-weight English and Chinese text-to-speech model with voice design, cloning and streaming output. Not applicable (entity) · unknown · unknown resource · en - ### [cohere-transcribe-03-2026](/frontier/model-releases/cohere-transcribe-2b/index.md) Creator not supplied; see original source. Hugging Face model card for CohereLabs/cohere-transcribe-03-2026, a 2B-parameter open speech recognition model for 14 languages. Not applicable (entity) · unknown · unknown resource · mul - ### [CosyVoice](/frontier/model-releases/cosyvoice/index.md) Creator not supplied; see original source. QwenAudio CosyVoice GitHub repo: multilingual voice generation model with inference, training and deployment. Not applicable (entity) · unknown · unknown resource · zh - ### [faster-whisper (Systran)](/frontier/model-releases/faster-whisper-systran/index.md) Creator not supplied; see original source. SYSTRAN faster-whisper GitHub repo: Whisper reimplementation on CTranslate2 for faster transcription. Not applicable (entity) · unknown · unknown resource · en - ### [Fun-Realtime-ASR-preview](/frontier/model-releases/fun-realtime-asr-preview/index.md) Creator not supplied; see original source. Artificial Analysis speech-to-text page for Alibaba, covering Fun-Realtime-ASR-preview: word error rate, speed and price compared with other models. Not applicable (entity) · unknown · unknown resource · en - ### [Gemini 2.5 Pro](/frontier/model-releases/gemini-2-5-pro/index.md) Creator not supplied; see original source. Artificial Analysis speech-to-text page for Google, covering Gemini 2.5 Pro: word error rate, speed and price compared with other models. Not applicable (entity) · unknown · unknown resource · en - ### [GigaAM (Sber)](/frontier/model-releases/gigaam-sber/index.md) Creator not supplied; see original source. Sber GigaAM GitHub repo: foundational models for Russian speech recognition. Not applicable (entity) · unknown · unknown resource · en - ### [GigaAM-v3: открытая SOTA-модель распознавания речи на русском языке](/frontier/model-releases/gigaam-v3-sber/index.md) Creator not supplied; see original source. Sber developers article on GigaAM-v3, an open MIT-licensed Russian speech recognition model released on GitHub and Hugging Face. Not applicable (entity) · unknown · unknown resource · ru - ### [Gladia Solaria-3](/frontier/model-releases/gladia-solaria-3/index.md) Creator not supplied; see original source. Gladia page for Solaria-3, its pre-recorded speech-to-text model for English, French, German, Spanish and Italian. Not applicable (entity) · unknown · unknown resource · en - ### [GPT Transcribe](/frontier/model-releases/gpt-transcribe/index.md) Creator not supplied; see original source. Artificial Analysis speech-to-text page for OpenAI, covering GPT Transcribe: word error rate, speed and price compared with other models. Not applicable (entity) · unknown · unknown resource · en - ### [Grok Voice Transcribe 2.0](/frontier/model-releases/grok-voice-transcribe-2-0/index.md) Creator not supplied; see original source. Artificial Analysis speech-to-text page for SpaceXAI, covering Grok Voice Transcribe 2.0: word error rate, speed and price compared with other models. Not applicable (entity) · unknown · unknown resource · en - ### [granite-4.0-1b-speech](/frontier/model-releases/ibm-granite-4-0-1b-speech/index.md) Creator not supplied; see original source. Hugging Face model card for ibm-granite/granite-4.0-1b-speech, IBM's compact speech recognition and translation model. Not applicable (entity) · unknown · unknown resource · mul - ### [IndicVoices](/frontier/model-releases/indicvoices/index.md) Creator not supplied; see original source. IndicVoices GitHub repo (AI4Bharat): 12,000-hour dataset of natural speech in Indian languages. Not applicable (entity) · unknown · unknown resource · en - ### [Kokoro TTS](/frontier/model-releases/kokoro-tts/index.md) Creator not supplied; see original source. Hugging Face model card for hexgrad/Kokoro-82M, an 82M-parameter open text-to-speech model, with weights, usage and license details. Not applicable (entity) · unknown · unknown resource · en - ### [Kyutai (Moshi)](/frontier/model-releases/kyutai-moshi/index.md) Creator not supplied; see original source. Kyutai: French open-science AI lab releasing audio models such as Moshi, Hibiki and Unmute, with papers. Not applicable (entity) · unknown · unknown resource · en - ### [MAI-Transcribe-1.5](/frontier/model-releases/mai-transcribe-1-5/index.md) Creator not supplied; see original source. Artificial Analysis speech-to-text page for Microsoft, covering MAI-Transcribe-1.5: word error rate, speed and price compared with other models. Not applicable (entity) · unknown · unknown resource · en - ### [MedASR (Google)](/frontier/model-releases/medasr-google/index.md) Creator not supplied; see original source. Google Research post on MedGemma 1.5 medical image interpretation and MedASR medical speech-to-text. Not applicable (entity) · unknown · unknown resource · en - ### [Mozilla Common Voice](/frontier/model-releases/mozilla-common-voice/index.md) Creator not supplied; see original source. Mozilla Common Voice GitHub repo: platform code for the crowdsourced multilingual voice dataset. Not applicable (entity) · unknown · unknown resource · mul - ### [NVIDIA Canary-Qwen-2.5B](/frontier/model-releases/nvidia-canary-qwen-2-5b/index.md) Creator not supplied; see original source. 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. Not applicable (entity) · unknown · unknown resource · en - ### [NVIDIA Parakeet TDT 0.6B v3](/frontier/model-releases/nvidia-parakeet-tdt-0-6b-v3/index.md) Creator not supplied; see original source. 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. Not applicable (entity) · unknown · unknown resource · mul - ### [OpenMOSS (Fudan)](/frontier/model-releases/openmoss-fudan/index.md) Creator not supplied; see original source. OpenMOSS GitHub organisation (Shanghai Innovation Institute and Fudan): MOSS, MOSS-TTSD and SpeechGPT code. Not applicable (entity) · unknown · unknown resource · en - ### [DeepFilterNet](/frontier/model-releases/podcast-speech-denoising-deepfilternet-usage-verified-free-code-documented-cli-a/index.md) Creator not supplied; see original source. DeepFilterNet GitHub repo: deep filtering noise suppression for speech audio. Not applicable (entity) · unknown · unknown resource · en - ### [pyannote Hugging Face organization](/frontier/model-releases/pyannote-diarization/index.md) Creator not supplied; see original source. pyannote Hugging Face organisation: speaker diarization and voice activity detection models. Not applicable (entity) · unknown · unknown resource · und - ### [Resonant-1](/frontier/model-releases/resonant-1/index.md) Creator not supplied; see original source. Artificial Analysis speech-to-text page for Reson8, covering Resonant-1: word error rate, speed and price compared with other models. Not applicable (entity) · unknown · unknown resource · en - ### [Scribe v2](/frontier/model-releases/scribe-v2/index.md) Creator not supplied; see original source. Artificial Analysis speech-to-text page for ElevenLabs, covering Scribe v2: word error rate, speed and price compared with other models. Not applicable (entity) · unknown · unknown resource · en - ### [Silero models](/frontier/model-releases/silero-models/index.md) Creator not supplied; see original source. Silero models GitHub repo: pretrained speech-to-text and text-to-speech models. Not applicable (entity) · unknown · unknown resource · en - ### [Silero VAD](/frontier/model-releases/silero-vad/index.md) Creator not supplied; see original source. Silero VAD GitHub repo: pretrained voice activity detection model for streaming audio. Not applicable (entity) · unknown · unknown resource · en - ### [smallest-python-sdk](/frontier/model-releases/smallest-ai-official-python-sdk-and-examples/index.md) Creator not supplied; see original source. Smallest AI Python SDK GitHub repo: official client for the Smallest AI speech API. Not applicable (entity) · unknown · unknown resource · en - ### [Smallest AI Pulse](/frontier/model-releases/smallest-ai-pulse/index.md) Creator not supplied; see original source. Artificial Analysis speech-to-text page for Smallest.ai, covering Smallest AI Pulse: word error rate, speed and price compared with other models. Not applicable (entity) · unknown · unknown resource · en - ### [Smallest AI Pulse Pro](/frontier/model-releases/smallest-ai-pulse-pro/index.md) Creator not supplied; see original source. Artificial Analysis speech-to-text page for Smallest.ai, covering Smallest AI Pulse Pro: word error rate, speed and price compared with other models. Not applicable (entity) · unknown · unknown resource · en - ### [Solaria-3](/frontier/model-releases/solaria-3/index.md) Creator not supplied; see original source. Artificial Analysis speech-to-text page for Gladia, covering Solaria-3: word error rate, speed and price compared with other models. Not applicable (entity) · unknown · unknown resource · en [Next page](/tags/voice-speech/page/2/index.md) [Plain-text Markdown copy](/tags/voice-speech/index.md)