Kokoro TTS

venice Text-to-speech default for Text-to-speech

Cheapest workhorse TTS — high-volume narration/transcripts where per-call cost matters more than best-in-class expressiveness. 54 voices across 9 languages.

Metered per call — price returned in meta.price
Published price
tts-kokoro
species_name
2026-10-10
Verified since
Call it

One request, the price in the response.

Pass species_name to pin this model; omit it and Fire uses the default for the endpoint. Every response carries meta.price.usd and meta.call_id.

curl -X POST https://fire.prosaga.net/v1/speech \
  -H "Authorization: Bearer $FIRE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"species_name":"tts-kokoro",
      "text":"Hello from Fire."}'


# → {"audio":"<base64>","format":"mp3","meta":{"price":{"usd":…}}}

Strengths

No strengths tagged yet.

Modality

In: text  ·  Out: audio

Lineage

Family hexgrad · genus kokoro · served by venice

Capabilities

modality
speech
Similar models

Same job, different trade-offs.

Call Kokoro TTS with one key.

Free to sign up. Pay only when you top up.