Inference APIs
Compare/Text-to-speech

Orpheus 3B vs Qwen3 TTS

Two open-weight text-to-speech models on the same endpoint and API key, so switching between them is a one-word change. Below: what each costs for three realistic workloads, how they differ, and measured speed.

Inference APIs prices are read live from the price list.

Short answer
  • Cost: Orpheus 3B is cheaper in all three workloads, by 25%.

Side by side

Orpheus 3BQwen3 TTS
Served byInference APIsInference APIs
Model authorCanopy LabsAlibaba Qwen
Model idcanopylabs/orpheus-3b-0.1-ftQwen/Qwen3-TTS
Price$19.50 / 1M characters$26.00 / 1M characters
CapabilitiesText to speech, Expressive, 8 voices, EnglishText to speech, 9 voices, Instruction control, MP3 / WAV, 10 languages
WeightsOpenOpen
StatusAvailableAvailable
LimitsNo per-minute or per-day request or token caps; usage draws on a prepaid balanceNo per-minute or per-day request or token caps; usage draws on a prepaid balance
300 characters → audio58.5 s—

What three workloads cost

List prices applied to the same work. The cheaper side of each row is in bold.

WorkloadOrpheus 3BQwen3 TTSDifference
One 1,000-word article (about 6,000 characters)$0.12$0.1625%
One hour of narration (about 54,000 characters)$1.05$1.4025%
One million characters (about 18 hours of speech)$19.50$26.0025%

Orpheus 3B is cheaper in all three workloads, by 25%.

When to choose which

Choose Orpheus 3B if
  • Cost is the deciding factor; it is cheaper in every workload above
  • Pre-rendered English narration where expressiveness matters
  • You want inline emotion tags such as <laugh> and <sigh>
  • Price per character matters most: Kokoro is five times cheaper
  • You need English voice variety: Kokoro has 54 voices, this model has 9
Choose Qwen3 TTS if
  • You want to steer tone and emotion with plain-language instructions ("speak slowly and calmly")
  • Ten languages from one model, including Korean, Russian and German, which Kokoro does not cover
  • Voice cloning from a short sample, which the host documents through a voice_id parameter
  • The speech is interactive and has to come back within a second or two

Measured speed

Median of three runs on 2026-09-16: a 300-character paragraph to mp3, timed from request to last byte. Expect ±30% with time of day. Method and raw numbers: speed measurements.

Trying both

Same endpoint, same key. Change one string:

cURL
for MODEL in "canopylabs/orpheus-3b-0.1-ft" "Qwen/Qwen3-TTS"; do
  curl -s https://api.inferenceapis.com/v1/audio/speech \
    -H "Authorization: Bearer $INFERENCE_API_KEY" -H "Content-Type: application/json" \
    -d "{\"model\": \"$MODEL\", \"input\": \"The quick brown fox jumps over the lazy dog.\"}" \
    --output "$(basename $MODEL).mp3"
done

FAQ

Which is cheaper, Orpheus 3B or Qwen3 TTS?

Orpheus 3B is cheaper in all three workloads, by 25%. The table above uses list prices: Orpheus 3B $19.50 / 1M characters; Qwen3 TTS $26.00 / 1M characters.

How do I switch between them?

They are on the same endpoint and key. Change the model field from canopylabs/orpheus-3b-0.1-ft to Qwen/Qwen3-TTS and nothing else.

Spotted a price or limit that has changed? Tell us and we will re-check the provider page.