{"slug":"agentsvc-io-api-v1-proxy-audio-transcribe-a6b50c","title":"Speech to text for agents","host":"agentsvc.io","method":"POST","resource":"https://agentsvc.io/api/v1/proxy/audio-transcribe","category":"image","description":"Speech to text for agents: 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_ur","price_listed":0.01,"price_asked":null,"state":"effects","state_label":"Not tested: has real-world effects","checks_7d":0,"answered_7d":0,"latency_ms_median":null,"reported_calls_30d":4,"reported_payers_30d":2,"networks":["eip155:137","eip155:42161","eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"audio_url":"https://agentsvc.io/samples/speech-en.mp3"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"audio_base64":{"description":"Audio file as base64; or use audio_url","type":"string"},"audio_url":{"description":"Public URL of the audio file","type":"string"},"language":{"description":"ISO 639-1 code like en or de, default auto-detect","type":"string"},"model":{"default":"small","description":"small is more accurate, base about twice as fast","enum":["small","base"],"type":"string"},"timestamps":{"default":true,"description":"Include segments with start and end seconds","type":"boolean"}},"required":[]},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"data":{"properties":{"duration_seconds":{"type":"number"},"language":{"type":"string"},"language_probability":{"type":"number"},"model":{"type":"string"},"model_license":{"type":"string"},"processing_ms":{"type":"integer"},"segments":{"items":{"properties":{"end":{"type":"number"},"start":{"type":"number"},"text":{"type":"string"}},"type":"object"},"type":"array"},"text":{"type":"string"}},"required":["text","language","duration_seconds"],"type":"object"},"success":{"type":"boolean"}},"required":["success","data"],"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[],"description_full":"Speech to text for agents: 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 call. Returns text, detected language, duration and segments with start and end seconds.","last_updated":"2026-10-15T18:53:55.956Z","schemes":["exact"]}