All projects matching “language detection”

Audio transcription and speech to text: transcribe a voice note, meeting, podcast or call recording into text with timestamps, in about 100 languages with automatic language detection. Runs OpenAI Whisper (small by default, base for speed) on agentsvc.io itself, the audio is deleted after the call. Send audio_url or audio_base64 (mp3, mp4, m4a, wav, ogg, webm, flac), up to 10 minutes and 24 MB per

Extract structured data from a URL or raw text into strict JSON matching a schema you provide. Fields the content doesn't support come back null - never an invented or approximate value, and an unmatchable schema returns an explicit error. Try GET /extract/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

NoJunk Speech transcribe: Transcribe audio (URL or base64, up to 20 MB / about 10 minutes) to text with timestamps, word count and detected language (Whisper large-v3-turbo).

Use when you need what is said in a public short-form video (TikTok, Instagram Reel, YouTube Short, Facebook), max 180s. Returns timestamped transcript, English translation if foreign, detected languages. Async: returns job_id + token, poll result_url. Charged only on delivery; failures cost nothing. Repeat videos return instantly.

Pay-per-use AI audio transcription API. Transcribe short MP3 and WAV audio files using Whisper Large V3 Turbo. No account or API key required. Pay with USDC on Base. 0.02 USDC per request. Maximum 120 seconds and 2 MB; MP3 and uncompressed PCM WAV only. Returns JSON: text, detected language, duration and timestamped segments. Charged only when a transcript is returned.

Machine translation for agents between 100 languages: send text (up to 5,000 chars), target_lang and optional source_lang (auto-detect by default) and get the translation. $0.001 USDC per started 1,000 characters on Base; failures are not charged. LibreTranslate/dTelecom-style {q, source, target} also accepted at /v1/translation. M2M100 1.2B. By DevX.

API Rescue - Detect API failures, validate responses against schema or baseline, diagnose causes, and propose code fixes and regression tests in the requested language.

Finds up to 100 faces in a JPEG or PNG at a URL with Amazon Rekognition and describes each: position, estimated age range, emotions, smile, glasses, beard, eyes and mouth open, pose and image quality. It does not identify anyone or compare faces.