falSpeech to textComing soon

fal-ai/cohere-transcribe

Name: fal-ai/cohere-transcribe
Brand: fal

fal-ai/cohere-transcribe is a speech to text tool from fal that runs in the background and returns structured JSON. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.000090279 per second. Measured from the input file. The final charge comes from usage.

Limits

Runs: In the background
Returns: json
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`audio_url` required	URL or file	—	URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg, flac.
`language`	one of en, fr, de, it, es, pt, el, nl, pl, zh, ja, ko, vi, ar	en	Language of the audio (ISO 639-1 code). Supported: en, fr, de, it, es, pt, el, nl, pl, zh, ja, ko, vi, ar.
`punctuation`	true or false	true	Whether to include punctuation and capitalization in the output.
`max_new_tokens`	number (whole) 1 to 1014	256	Maximum number of tokens to generate per audio chunk.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/cohere-transcribe",
    "input": {
      "audio_url": "https://storage.googleapis.com/falserverless/model_tests/whisper/dinner_conversation.mp3"
    }
  }'