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.
- Cost: Orpheus 3B is cheaper in all three workloads, by 25%.
Side by side
| Orpheus 3B | Qwen3 TTS | |
|---|---|---|
| Served by | Inference APIs | Inference APIs |
| Model author | Canopy Labs | Alibaba Qwen |
| Model id | canopylabs/orpheus-3b-0.1-ft | Qwen/Qwen3-TTS |
| Price | $19.50 / 1M characters | $26.00 / 1M characters |
| Capabilities | Text to speech, Expressive, 8 voices, English | Text to speech, 9 voices, Instruction control, MP3 / WAV, 10 languages |
| Weights | Open | Open |
| Status | Available | Available |
| Limits | No per-minute or per-day request or token caps; usage draws on a prepaid balance | No per-minute or per-day request or token caps; usage draws on a prepaid balance |
| 300 characters → audio | 58.5 s | — |
What three workloads cost
List prices applied to the same work. The cheaper side of each row is in bold.
| Workload | Orpheus 3B | Qwen3 TTS | Difference |
|---|---|---|---|
| One 1,000-word article (about 6,000 characters) | $0.12 | $0.16 | 25% |
| One hour of narration (about 54,000 characters) | $1.05 | $1.40 | 25% |
| One million characters (about 18 hours of speech) | $19.50 | $26.00 | 25% |
Orpheus 3B is cheaper in all three workloads, by 25%.
When to choose which
- 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
- 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:
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"
doneFAQ
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.
