Models tagged "speech-to-text"

🤖 Model 🔊

zsxkib/audio-flamingo-3

Answer questions about audio with text output, performing step-by-step reasoning across speech, music, and sound effects...

🔊 • speech-to-text • music-understanding • audio-analysis • 774 runs

🤖 Model 📝 → 🔊

zsxkib/kimi-audio-7b-instruct

Transcribe audio and generate spoken or textual responses from an audio input. Accepts an audio clip and optional text p...

📝 → 🔊 • speech-to-text • text-to-speech • audio-to-audio • 3.3K runs

🤖 Model 🔊

mistralai/voxtral-mini-3b

Transcribe, translate, and understand speech from audio input, returning text. Switch between transcription and understa...

🔊 • speech-to-text • speech-translation • audio-understanding • 35 runs

🤖 Model 📝 → 🔊

ictnlp/llama-omni

Answer spoken questions and return both text and spoken responses. Accepts input speech audio (with an optional instruct...

📝 → 🔊 • speech-to-text • text-to-speech • audio-to-audio • 60.1K runs

🤖 Model 🔊

nvidia/canary-qwen-2.5b

Transcribe long-form audio to text with optional timestamps and prompt-driven analysis. Accept an audio file and return...

🔊 • speech-to-text • audio-analysis • 5.0K runs

🤖 Model 📝 → 🔊

lucataco/qwen2.5-omni-7b

Chat and analyze across text, images, audio, and video, returning text responses and optional synthesized speech. Accept...

📝 → 🔊 • text-generation • video-to-text • text-to-speech • 13.9K runs

🤖 Model

jacksoby/whisperx

Transcribe spoken audio to text. Accepts an audio file and returns a structured transcript with segments plus per-word t...

speech-to-text • 596 runs

🤖 Model

vaibhavs10/incredibly-fast-whisper

Transcribe or translate audio to text. Accepts an audio input and returns a transcript with chunk- or word-level timesta...

speech-to-text • speech-translation • speaker-diarization • 17.2M runs

🤖 Model

openai/gpt-4o-transcribe

Transcribe audio to text using GPT-4o. Accepts an audio file with optional language hint and prompt for style or segment...

speech-to-text • 12.6K runs

🤖 Model

openai/whisper

Transcribe speech from an audio file to text. Support multilingual speech recognition with automatic language detection...

speech-to-text • speech-translation • 131.7M runs

🤖 Model

thomasmol/whisper-diarization

Transcribe audio to text with speaker diarization. Accepts an audio file, direct URL, or base64 audio and returns JSON w...

speech-to-text • speaker-diarization • 3.1M runs

🤖 Model

openai/gpt-4o-mini-transcribe

Transcribe audio to text. Accepts an audio file with an optional language hint (ISO-639-1) and an optional prompt to gui...

speech-to-text • transcription • 1.3K runs

🤖 Model

victor-upmeet/whisperx

Transcribe speech audio to text with word-level timestamps and optional speaker diarization. Takes an audio file and out...

speech-to-text • speaker-diarization • 4.4M runs

🤖 Model

nvidia/parakeet-rnnt-1.1b

Transcribe English speech from audio into text (ASR). Handle noisy backgrounds and silent segments, outputting lowercase...

speech-to-text • asr • 18.1K runs

🤖 Model 🎥

adidoes/whisperx-video-transcribe

Transcribe speech from online videos into text. Accepts a video input from supported sites and returns a JSON transcript...

🎥 • speech-to-text • video-auto-captioning • 19.6K runs

🤖 Model 🔊

aihilums/sehatsanjha

Transcribe multi-speaker audio into a structured dialogue with speaker labels and section headers, returning JSON. Accep...

🔊 • speech-to-text • speaker-diarization • audio-to-json • 36.7K runs

🤖 Model 📝 → 🔊

cjwbw/seamless_communication

Translate and transcribe speech and text across many languages, returning text and optionally synthesized speech. Suppor...

📝 → 🔊 • speech-translation • speech-to-text • text-to-speech • 87.8K runs

🤖 Model

daanelson/whisperx

Transcribe audio to text with fast, batched WhisperX ASR, including word-level timestamps and speaker diarization. Accep...

speech-to-text • speaker-diarization • 88.4K runs

🤖 Model

m1guelpf/whisper-subtitles

Generate SRT or VTT subtitles and a full transcript from an audio file. Use OpenAI Whisper with selectable models (tiny....

speech-to-text • subtitle-generation • language-identification • 73.8K runs

🤖 Model

ibm-granite/granite-speech-3.3-8b

Transcribe and translate speech from audio into text. Accept audio and an optional prompt and return text transcripts or...

speech-to-text • speech-translation • 12.8K runs