Voice and music · by Groq

Groq

Transcribe audio or turn text into speech at very high speed.

text, image → text, data, code · speech → text · text → speech
Way in
Official APISign up yourself, api key
To start
$free plan with lower limits (per docs rate-limit page)
Runs
In the cloudAlso through Hugging Face, OpenRouter, vercel-ai-gateway
Checked
Nov 3, 2026Prices as of that day

What it can do 3

Call hosted LLMs through one OpenAI-compatible endpointDeveloper plan: 250K TPM, 1K RPMtext, image → text, data, codegpt-oss-120b $0.15/$0.60 (~500 tok/s), gpt-oss-20b $0.075/$0.30 (~1,000 tok/s) per 1M
Transcribe audio fast100 MB files, 300-400 RPMspeech → textwhisper-large-v3 $0.111/h, whisper-large-v3-turbo $0.04/h
Synthesize speech (Orpheus)50K TPMtext → speechOrpheus v1 English $22 per 1M characters; Orpheus Arabic (Saudi) $40 per 1M characters

Does the same job

Prices and limits as of Nov 3, 2026, from Groq’s own pages. They change; check before you rely on them.Not affiliated with Groq. Not advice.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.