Melhores modelos de conversão de fala em texto e transcrição

Classificações de modelos atualizadas com base em dados reais de uso.

Os modelos são classificados pelo total de caracteres transcritos processados pela API do OpenRouter nos últimos 7 dias. Exibindo os 25 melhores modelos. As classificações medem o uso no OpenRouter e refletem a adoção, não a qualidade do modelo ou o desempenho em testes de referência.

Modelos de fala para texto convertem áudio falado em texto para transcrição, legendas, resumos de reuniões, análise de chamadas e aplicativos controlados por voz. Esta coleção classifica os modelos de transcrição pelo uso no OpenRouter na última semana. Os melhores modelos atualmente são Whisper Large V3 Turbo, MAI-Transcribe 2 e Whisper Large V3. Compare precisão, velocidade, suporte a idiomas e custo para encontrar o modelo certo para seu fluxo de trabalho de áudio.

Principais modelos de fala para texto no OpenRouter

Whisper Large V3 Turbo is an optimized version of OpenAI's Whisper Large V3 speech recognition model, designed for speed and cost efficiency. It supports transcription across 99+ languages with a 12% word error rate, and accepts common audio formats including mp3, mp4, wav, webm, flac, and ogg. Achieves real-time speed factors up to 216x, making it well-suited for latency-sensitive and high-throughput transcription workloads.

por openaiUS$ 0,000003/second

MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI, ranked #1 on the FLEURS multilingual benchmark. It supports 60 languages with automatic language identification, code switching for mixed-language speech, speaker diarization, word-level timestamps, keyword biasing for domain-specific terminology, and configurable verbatim or clean transcription styles. It is suited for captions, call transcription, subtitling, accessibility, and other voice-enabled applications, and is faster than MAI-Transcribe-1.5 on long-form audio.

On OpenRouter, set response_format to "verbose_json" for segment timestamps, and add timestamp_granularities: ["word"] for word-level timestamps. Set provider.options.azure.diarization.enabled to true for speaker labels, provide keywords through provider.options.azure.phraseList.phrases, and select a transcription style through provider.options.azure.enhancedMode.modelOptions.transcribeStyle. See the speech-to-text guide.

por microsoftUS$ 0,10/hour
Favicon de openai

OpenAI: Whisper Large V3

1,82B caracteres

Whisper Large V3 is OpenAI's open-source automatic speech recognition model offering both audio transcription and translation. It supports 99+ languages and accepts common audio formats including mp3, mp4, wav, webm, flac, and ogg. With 1,550M parameters, it achieves a 10.3% word error rate and is well-suited for noise-robust, multilingual transcription in demanding conditions. Supports timestamp granularities at word and segment levels.

por openaiUS$ 0,000008/second
Favicon de elevenlabs

ElevenLabs: Scribe v2

939M caracteres

ElevenLabs Scribe v2 is a speech-to-text model that transcribes audio in 90+ languages with word-level timestamps, optional speaker diarization, and audio-event tagging.

por elevenlabsUS$ 0,000061/second

GPT-4o Mini Transcribe is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities. It's priced per token (input and output), making it suitable for high-volume transcription workflows that benefit from token-level billing transparency at a lower cost point.

por openaiUS$ 1,25/M entrada US$ 5/M saída
Favicon de qwen

Qwen: Qwen3 ASR 1.7B

224M caracteres

Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference plus segment-level and word-level timestamps.

por qwenUS$ 0,000008/second
Favicon de openai

OpenAI: Whisper 1

180M caracteres

Whisper is OpenAI's open-source automatic speech recognition model, available via API as whisper-1. It supports transcription and translation across 50+ languages from audio files up to 25 MB. Accepts formats including mp3, mp4, wav, and webm. Priced per minute of audio duration, billed to the nearest second.

por openaiUS$ 0,0001/second

Universal-3.6 Pro is AssemblyAI's speech-to-text model and the successor to Universal-3.5 Pro, served here through AssemblyAI's Sync API. Compared with Universal-3.5 Pro, AssemblyAI reports 30% fewer errors on short conversational utterances, 12% fewer errors on average across supported languages, 14 newly supported languages, and better recognition and formatting of entities such as phone numbers, addresses, emails, and codes. It returns a complete transcript with word-level timestamps in a single synchronous response for audio up to 20 minutes, accepts WAV and compressed input (MP3, M4A, AAC, Ogg/Opus, FLAC, and WebM), and supports free-text prompting, keyterms, and conversation context to steer transcription toward domain vocabulary.

por assemblyaifrom US$ 0,000083/second
Favicon de deepgram

Deepgram: Nova-3

121M caracteres

Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual transcription support.

por deepgramfrom US$ 0,000072/second
Favicon de openai

OpenAI: GPT Transcribe

112M caracteres

GPT Transcribe is a high-accuracy speech-to-text model from OpenAI. It is suited for recorded audio, streamed file transcription, and committed Realtime turns, with free-form context, keyword hints, and multiple language hints for specialized terms and multilingual speech.

por openaiUS$ 0,000075/second
Favicon de qwen

Qwen: Qwen3 ASR 0.6B

89,6M caracteres

Qwen3 ASR 0.6B is a compact automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference plus segment-level and word-level timestamps.

por qwenUS$ 0,000003/second

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio can be up to one hour, or 30 minutes when timestamps or diarization are enabled.

por googleUS$ 2/M entrada US$ 12/M saída

Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across all official EU languages and achieves a 6.34% average word error rate on the HuggingFace Open ASR Leaderboard. Returns transcribed text with punctuation and segment timestamps.

por nvidiaUS$ 0,000017/second

Nemotron 3.5 Transcribe is an open-weight speech recognition model from NVIDIA, a 30B mixture-of-experts with about 4B active parameters. It transcribes recordings of up to one hour in 40 languages, with speaker attribution, speech translation, and prompt-guided vocabulary and style.

por nvidiaUS$ 0,000017/second
Favicon de openai

OpenAI: GPT-4o Transcribe

54,9M caracteres

GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.

por openaiUS$ 2,50/M entrada US$ 10/M saída

Muse Voice Transcribe 1.0 is a synchronous speech-to-text model from Meta. It is suited for push-to-talk, endpointing, and speaker-aware transcription, with keyword biasing for domain terms and language biasing through language-name hints. It accepts mono 16-bit PCM WAV audio at 16 kHz or 24 kHz for recordings up to 10 minutes. It does not provide word-level timestamps or confidence scores, and other audio formats must be converted to WAV before upload.

por metaUS$ 0,00005/second

Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for transcribing meetings, voice notes, podcasts, and other spoken content.

por mistralaiUS$ 0,00005/second
Favicon de x-ai

SpaceXAI: Grok STT 2.0

41,3M caracteres

Grok STT 2.0 is a speech-to-text model from SpaceXAI and the successor to Grok STT 1.0. It is suited for transcription workloads that need word-level timestamps, optional speaker diarization, and multichannel audio.

por x-aiUS$ 0,000028/second

Voxtral Small Transcribe 3 is Mistral's flagship speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization, and supports context biasing for domain-specific vocabulary. Suited for high-accuracy multilingual transcription of meetings, interviews, media, and support calls.

por mistralaiUS$ 0,000067/second

Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain terms. It is small enough to self-deploy in resource-constrained environments, and fits meeting notes, call analytics, and voice-agent pipelines where cost matters.

por mistralaiUS$ 0,000058/second

Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice agents, and multilingual transcription pipelines.

por nvidiaUS$ 0,000003/second

Transcribe 1 Pro is a speech-to-text model from Fish Audio tuned for interviews, meetings, and podcasts. It labels speakers with inline speaker markers, preserves emotion and vocal-event cues such as [laughter], detects language automatically, and can return timestamped word-level segments.

por fish-audioUS$ 0,0001/second

Universal-3.5 Pro is AssemblyAI's speech-to-text model served through its Sync API, returning a complete transcript with word-level timestamps in a single synchronous response for audio up to 20 minutes. It accepts WAV and compressed input (MP3, M4A, AAC, Ogg/Opus, FLAC, and WebM) and supports free-text prompting, keyterms, and conversation context to steer transcription toward domain vocabulary.

por assemblyaifrom US$ 0,000083/second

ElevenLabs Scribe v2 Medical is a speech-to-text model tuned for clinical and medical terminology, with word-level timestamps, optional speaker diarization, and audio-event tagging.

por elevenlabsUS$ 0,000061/second

MAI-Transcribe 1.5 is a multilingual speech-to-text model from Microsoft AI. It is suited for captions, call transcription, subtitling, accessibility, and other voice-enabled applications, with reliable transcription across 43 languages, diverse accents, and noisy real-world audio. It supports automatic language identification and keyword biasing for domain-specific terminology, and improves long-form transcription speed over MAI-Transcribe-1. Speaker diarization is not supported.

por microsoftUS$ 0,36/hour

Perguntas frequentes

Explorar mais coleções