# Lemonfox.ai Speech-to-text and text-to-speech APIs for developers building audio workflows. - Findings24: - Site: - Preços: Freemium - Categorias: Voz para Texto, API de áudio com IA, Gerador de voz com IA ## O que é Lemonfox.ai? Lemonfox.ai provides APIs for converting audio to text and text to speech. Its speech-to-text service transcribes audio using the Whisper large-v3 model, supports more than 100 languages, and can translate through the API. Optional speaker diarization identifies different speakers in a recording. A separate text-to-speech API generates spoken audio from text. The APIs are intended for developers integrating speech workflows into their applications; a browser-based transcription option, Transcripo, is also linked for people who are not developers. ## O que Lemonfox.ai pode fazer? ### Speech transcription Convert audio files to text through an API powered by the Whisper large-v3 speech recognition model. ### 100+ language support Transcribe audio in more than 100 languages, with translation available through the speech-to-text API. ### Speaker diarization Use the diarization option to identify different speakers in an audio recording. ### Text-to-speech generation Generate speech from text using a separate Lemonfox.ai API; the service page describes streaming and word-level timings. ### API pricing by credits The site describes a monthly plan with 10 million credits and additional credit usage charged separately; credits cover either speech-to-text or text-to-speech workloads. ### Data handling options The site says data is deleted immediately after processing and that EU-based processing is available. ## Casos de uso ### Transcribe multilingual recordings Send audio files to the speech-to-text API to produce text from recordings in supported languages, with translation available when needed. ### Separate speakers in a recording Use diarization when reviewing interviews, discussions, or other audio where identifying changes between speakers matters. ### Add generated speech to an application Integrate the text-to-speech API to turn application text into audio, including streaming workflows described by the service. ### Offer transcription without API integration People who do not need a developer API can use the linked Transcripo service to convert speech to text. ## Perguntas frequentes ### Which speech recognition model powers transcription? The website identifies Whisper large-v3 as the speech recognition model used by the speech-to-text API. ### Can the API handle multiple languages or translation? The speech-to-text API supports more than 100 languages, and the site says translation is available through the API. ### Can a transcript identify different speakers? Yes. Speaker recognition is available as a diarization option for identifying different speakers in audio. ### Is there a way to transcribe without building an API integration? The Lemonfox.ai site links to Transcripo as an option for people who are not developers. ### How is API usage billed? The site describes a $5 monthly plan that includes 10 million credits, plus $0.50 for each additional 1 million credits. It states that 10 million credits correspond to 30 hours of speech-to-text or 2 million text-to-speech characters. ## Informações rápidas - **Product type**: Speech-to-text and text-to-speech APIs - **Primary users**: Developers integrating speech capabilities - **Speech recognition model**: Whisper large-v3 - **Language support**: More than 100 languages - **Trial**: First month free, as stated on the website - **Processing**: Immediate data deletion is stated; EU-based processing is available