Speech: To Text
Facts
- Model name
- speech-to-text
- Maker
- Kotoba-technologies
- Context window
- 1 tokens
- Price
- $0.00012 per second
- Providers
- 1 independent provider
- Regions
- us
Providers
- Architect: us, $0.00012 per second, 1 tokens of context
Request
curl https://router.inference.ai.exchange/v1/audio/transcriptions \
-H "Authorization: Bearer $LIQUID_API_KEY" \
-F model=speech-to-text \
-F [email protected]
Questions
- What is Speech: To Text?
- Speech: To Text is a model from Kotoba-technologies.
- How much does Speech: To Text cost?
- Offers now ask $0.00012 second.
- What is the context length of Speech: To Text?
- The largest offer takes 1 input tokens. One job can generate up to 1 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can Speech: To Text do?
- Its providers list Audio input, Text.
- What inputs and outputs does Speech: To Text support?
- Audio → Text · transcript.
- Which providers serve Speech: To Text?
- 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
- How do I call Speech: To Text?
- Send "speech-to-text" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was Speech: To Text listed?
- The exchange first listed it on 10/22/2026. This is not its release date.
Related pages