Sign inGet started
ElevenLabsSpeech to speechAvailable now

eleven_multilingual_sts_v2

eleven_multilingual_sts_v2 is a speech to speech tool from ElevenLabs that runs in the background and returns audio. Pay as you go from $0.000156 per credit, with one API key.

Try itfrom $0.000156 / credit

Pricing

$0.156 per minute. Measured from the input file, rounded up. The final charge comes from usage.

Limits

Runs
In the background
Returns
audio
Longest queue wait
3600s
Run deadline
1800s
Largest inline input
1024 KB
Largest input file
100 MB
Largest output
4768 MB
Outputs per run
16

Input

FieldKindDefaultDescription
audio requiredURL or file—The audio file which holds the content and emotion that will control the generated speech.
voice_id requiredtext—Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
seednumber (whole)
0 to 4294967295
—If specified, our system will make a best effort to sample deterministically. Must be integer between 0 and 4294967295.
file_formatone of
pcm_s16le_16, other
otherThe format of input audio. Options are 'pcm_s16le_16' or 'other'. For `pcm_s16le_16`, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order.
output_formatone of
alaw_8000, mp3_22050_32, mp3_24000_48, mp3_44100_128, mp3_44100_192, mp3_44100_32, mp3_44100_64, mp3_44100_96, opus_48000_128, opus_48000_192, opus_48000_32, opus_48000_64, opus_48000_96, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, pcm_8000, ulaw_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000, wav_8000
mp3_44100_128Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32.
voice_settingsJSON—Voice settings overriding stored settings for the given voice. They are applied only on the given request.
remove_background_noisetrue or falsefalseIf set, will remove the background noise from your audio input using our audio isolation model.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "elevenlabs",
    "model": "eleven_multilingual_sts_v2",
    "input": {
      "audio": "<audio>",
      "voice_id": "<voice_id>"
    }
  }'