Speech-to-text API

A speech-to-text API hosted in Europe

Turn audio files, video files or URLs into timestamped text. Presigned upload or source_url, JSON/SRT/VTT output, 100% European processing and storage.

request
# 1. Get a presigned upload URL
curl https://api.techtuel.com/v1/uploads \
  -H "Authorization: Bearer $TECHTUEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "content_type": "audio/mpeg", "filename": "meeting.mp3", "size_bytes": 18400000 }'

# 2. Transcribe the uploaded file
curl https://api.techtuel.com/v1/transcriptions \
  -H "Authorization: Bearer $TECHTUEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "upload_id": "up_abc123" }'
response
{
  "id": "job_9f2c…",
  "status": "completed",
  "title": "The Daily Standup — Episode 42",
  "language": "en",
  "minutes": 12.5,
  "transcript": "Hello and welcome…",
  "segments": [
    { "start_seconds": 0, "text": "Hello and welcome" },
    { "start_seconds": 4.2, "text": "to the Daily Standup" }
  ]
}

A speech recognition API has to get three things right: transcribe accurately, return a structure you can actually use, and respect your data. Techtuel covers all three, with processing and hosting entirely inside Europe.

Upload a file through a presigned S3 URL, or point at a public URL: the API returns text with timestamped segments, ready to become subtitles or a meeting summary. Common audio and video formats are accepted (MP3, M4A, WAV, MP4, WebM, MKV and more).

Files are deleted after processing and nothing is reused for training. This is an API you can drop into a GDPR-bound product without contortions.

Why this API

European end to end

Processing and hosting in France (OVHcloud, Scaleway), no US cloud dependency. Files deleted after processing, fit for a GDPR-bound product.

Upload or URL

Upload a file through a presigned URL, or transcribe a public URL directly. Both paths return the same JSON.

Timestamped segments

Every response carries segments with their start_seconds — the direct basis for SRT/VTT subtitles.

Pricing you can read

Free100 credits/month (~50 min of audio), no credit card
Pro2000 credits/month (~1000 min of audio), 120 req/min per key

Frequently asked questions

Which file formats are supported?+

Audio: MP3, M4A, AAC, OGG, Opus, WAV, WebM, FLAC (up to 200 MiB). Video: MP4, MPEG, WebM, QuickTime, MKV (up to 1 GiB).

How do I upload a file?+

Call POST /v1/uploads to get a presigned S3 URL, PUT the file to it, then create the transcription with the returned upload_id.

Where is my data processed?+

Processing and hosting are 100% European. Uploaded files are deleted after processing and are never reused.

Which languages are supported?+

Audio is transcribed in its original language. English and French are fully supported.

Other ways to use the API

Free trial, no credit card

Generate an API key and transcribe your first source in under a minute. A free monthly quota lets you test under real conditions.

Start with the API