Create speech | OpenRouter

Synthesizes audio from the input text. Returns a raw audio bytestream in the requested format (e.g. mp3, pcm, wav).

AuthorizationBearer

API key as bearer token in Authorization header

This endpoint expects an object.

inputstringRequired

Text to synthesize

modelstringRequired

TTS model identifier

voicestringRequired

Voice identifier (provider-specific).

providerobjectOptional

Provider-specific passthrough configuration

response_formatenumOptionalDefaults to pcm

Audio output format

Allowed values:

speeddoubleOptional

Playback speed multiplier. Only used by models that support it (e.g. OpenAI TTS). Ignored by other providers.

Audio bytes stream

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

404

Not Found Error

429

Too Many Requests Error

500

Internal Server Error

502

Bad Gateway Error

503

Service Unavailable Error

$	curl -X POST https://openrouter.ai/api/v1/audio/speech \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"input": "Hello world",
>	"model": "elevenlabs/eleven-turbo-v2",
>	"voice": "alloy",
>	"response_format": "pcm",
>	"speed": 1
>	}'

$	curl -X POST https://openrouter.ai/api/v1/audio/speech \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"input": "Hello world",
>	"model": "elevenlabs/eleven-turbo-v2",
>	"voice": "alloy",
>	"response_format": "pcm",
>	"speed": 1
>	}'