joshu

Fish Audio: S2.1 Pro text to speech

From Fish Audio, through Joshu Data Bodega.

Part of Voice generation fishaudio s2 1 pro generate.

Price
$0.0000165 per call$0.02 per 1,000 calls

No calls measured in the last 30 days.

Prices include the router's 10% markup and are paid from the usage wallet. Checked on November 11, 2026.

Inputs

  • textstring, required

  • top_pnumber, optional

  • formatstring: mp3, wav, pcm, opus, optional

  • latencystring: low, normal, balanced, optional

  • prosodyobject, optional

  • normalizeboolean, optional

  • mp3_bitrateinteger: 64, 128, 192, optional

  • sample_rateinteger: 8000, 16000, 24000, 32000, 44100, 48000, optional

    Supported output rates depend on the selected format.

  • temperaturenumber, optional

  • chunk_lengthinteger, optional

  • opus_bitrateinteger: -1000, 24000, 32000, 48000, 64000, optional

  • reference_idstring, optional

    Omit for Fish's default voice. On treg's key each id must be owned by the current team or verified by Fish as public.

  • max_new_tokensinteger, optional

  • min_chunk_lengthinteger, optional

  • repetition_penaltynumber, optional

  • early_stop_thresholdnumber, optional

  • condition_on_previous_chunksboolean, optional

Call it

Router call with a router API key
curl https://hello.joshu.me/api/router/call \
  -H "Authorization: Bearer $JOSHU_ROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "endpoint": "fishaudio.tts.s2-1-pro",
    "params": {
      "text": "This is a Fish Audio test.",
      "format": "mp3"
    }
  }'