Speechmatics TTS $0.011 per 1,000 characters vs Sume TTS limits

Speechmatics' pricing page lists text-to-speech at $0.011 per 1,000 characters, with the first 1 million characters free. At that rate a 20,000-character script costs $0.22, and the first 50 such scripts would be free. Sume TTS accepts up to 20,000 characters per request but publishes no TTS rate in its docs, so measure a real job on your balance.

The Speechmatics line

Speechmatics' page is the source for the rate and free allowance.

Sume TTS request

Choose a voice from a Sume avatar or voice.id, set language for non-English text, and pick a container. Audio over 1,200 seconds fails and is not charged.

import os, requests

r = requests.post(
    "https://api.sume.com/v1/tts-1.0/generate",
    headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}",
             "Idempotency-Key": "tts-demo-001"},
    json={"transcript": "Welcome back. Today we cover three updates.",
          "avatar_id": os.environ["SUME_AVATAR_ID"],
          "generation_config": {"speed": 0.95, "emotion": "warm"},
          "output_format": {"container": "mp3", "sample_rate": 44100,
                            "bit_rate": 128000}},
)
print(r.status_code, r.json())

Making the comparison honest

Quality differs by voice, language and script, which a price table cannot show. Generate the same three paragraphs on each service, then compare the charge and the sound.

Worked example

The free million characters go further than you might expect.

• 20,000 characters at $0.011 per 1,000 is $0.22.
• 1 million characters is 50 such requests, free on Speechmatics' page.
• 100 requests after the free allowance would cost $22.00 in characters alone.

Checklist before you commit

Price is one input; voice choice and language support matter just as much, so listen before deciding.

• Check language coverage.
• Check output formats.
• Re-read the pricing page before launch.