OpenAISpeech to textAvailable now

gpt-4o-mini-transcribe

Name: gpt-4o-mini-transcribe
Brand: OpenAI
Availability: InStock

gpt-4o-mini-transcribe is a speech to text tool from OpenAI that runs in the background and returns structured JSON. Pay as you go from $0.000001625 per token, with one API key.

Try itfrom $0.000001625 / token

Pricing

Up to $0.039 per run at the default inputs. $1.625 per 1M input tokens, $6.50 per 1M output tokens. 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: 25 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`file` required	URL or file	—	The audio file to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. At most 25 MB.
`prompt`	text	—	An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
`include`	list	—	Additional information to include in the transcription response. `logprobs` will return the log probabilities of the tokens in the response to understand the model's confidence in the transcription.
`language`	text	—	The language of the input audio. Supplying the input language in ISO-639-1 (e.g. `en`) format will improve accuracy and latency.
`temperature`	number 0 to 1	0	The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

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": "openai",
    "model": "gpt-4o-mini-transcribe",
    "input": {
      "file": "<file>"
    }
  }'