Voice and music · by OpenRouter
OpenRouter Speech
Switch between 38 text-to-speech engines with one account.
text → speech · search → data · speech, text → speech
- Way in
- Official APISign up yourself, api key
- To start
- $free variants of HeyGen Voice Turbo and Fish S2.1 Pro
- Runs
- In the cloud
- Checked
- Nov 3, 2026Prices as of that day
What it can do 3
Synthesize speech from any of ~38 routed TTS models with one keyoutput mp3 or pcm (some providers pcm-only or mp3-only)text → speechpass-through per model, e.g. Kokoro $0.62/1M chars, Gemini 3.8 Flash TTS $9/1M audio tokens, Eleven v4 $80/1M chars; free: heygen-voice-1-turbo:free, fish-audio/s2.1-pro-free
List TTS models with prices and capability flagssearch → datafree (keyless GET)
Clone or design a voice per request from reference audiospeech, text → speechper model
Does the same job
Prices and limits as of Nov 3, 2026, from OpenRouter’s own pages. They change; check before you rely on them.Not affiliated with OpenRouter. Not advice.Something wrong?