Head to head · Text-to-speech · October 2026 research run

Murf TTS API + MCP vs Soniox Text-to-Speech

Murf TTS API + MCP and Soniox Text-to-Speech score within a point of each other on agent readiness, 72 (BB) and 71.8 (BB). Soniox Text-to-Speech leads on agent ergonomics, security & auth and transparency & trust. Both do text-to-speech.

Best text-to-speech APIs for AI agents · All 148 tts comparisons

Which one, for what

Murf TTS API + MCP BB

Best for Budget voice-agent output where 2 to 5 concurrent streams are enough, or for studio-style renders on Gen2.

Ahead on

  • Payments & pricing, 60 against 30
  • Maintenance & community, 73 against 63

Also in its favour

  • Runs on your own machine
  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5

Watch for

Falcon 2.1 concurrency is 2 outside US-East on free and pay as you go, 5 on US-East

Soniox Text-to-Speech BB

Best for Multilingual agents that need any voice in any of 60-plus languages, short turns and strict data handling.

Ahead on

  • Agent ergonomics, 78 against 71
  • Security & auth, 87 against 68
  • Transparency & trust, 73 against 67

Watch for

Audio stops at 2 minutes per request or stream and the cap can't be raised

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Murf TTS API + MCP +30

Murf TTS API + MCP 60

No x402, MPP or L402 (0). Falcon 2 at 1 cent per 1,000 characters and Gen2 at $0.03, published in the docs without a login (20). 100,000 free characters with no time limit behind a Get Free API Key button. We found no card step in the docs or FAQ (20). A person signs up in a browser to get the key (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Soniox Text-to-Speech 30

No x402, MPP or L402 (0). Token prices published without a login, $4.00 per 1M input tokens and $21.50 per 1M output tokens, which Soniox puts at about $0.70 an hour, re-read on 2 November (20). No free credits for new accounts found (0). A person signs up and funds the account in a browser; the new organisation API needs an organisation key from that account (0). 0 + 20 + 0 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Security & auth Soniox Text-to-Speech +19

Murf TTS API + MCP 68

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. One api-key header, plus a generate-token endpoint for short-lived client tokens. No key scopes found (23 of 30). The docs say customer text and audio never feed Murf's model training (20). Download links last 72 hours by the TTS overview and 24 hours by the Enterprise FAQ, and encodedAsBase64 returns audio with nothing stored, so zero retention is self-serve but not the default (10 of 15). The dashboard shows daily and monthly usage, not per-call logs (5 of 15). SOC 2 Type II, ISO 27001 and ISO 42001 on the security page. No security.txt, disclosure policy or bug bounty found (10 of 20).

Soniox Text-to-Speech 87

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. Project API keys now carry permissions per resource (TTS real-time, cloned voices, usage, model listing, temporary keys, with read and write levels), a missing permission returns 403 permission_denied, and an organisation API key can list, create and delete project keys. Temporary keys for browsers expire and are scoped to a usage_type (30; was 25). Soniox says audio and text are never used to improve its models (20). Nothing is stored unless you ask, and logs carry no content (15). Per-request usage logs record model, duration, tokens and the client reference id, readable through GET /v1/usage-logs, as soniox-stt reads them (10 of 15; was 5). SOC 2 Type 2, ISO/IEC 27001:2022 and HIPAA listed on the security page. The Python SDK's SECURITY.md (since May 2026) gives a disclosure route by email, GitHub, a maintainer or Discord. soniox.com/.well-known/security.txt answers 404 and no bug bounty was found (12 of 20; was 10). 30 + 20 + 15 + 10 + 12 = 87.

Maintenance & community Murf TTS API + MCP +10

Murf TTS API + MCP 73

Read as a model. Newest changelog entry 2026-10-27 (List Voices takes a model), after Falcon 2.1 on 2026-10-19 (30). Seven dated changelog entries in the 90 days from 3 August, on 5, 9, 13, 15, 19, 22 and 27 October, plus murf-mcp 0.1.14 on 2026-08-20 (10). Gen2 streaming was switched off on 2026-10-05 after a 20 July notice that named only the 16 August deprecation date, and on 19 October falcon-2 began serving Falcon 2.1, announced the same day (0 of 10). Public changelog and a help centre (10 of 15). The Python SDK had no open issues on 1 October, per that check, not re-read on 1 November (8 of 10). Official SDK in Python only, 2.3.0 still the newest tag on 1 November, from 2026-03-05 (8 of 15). Fern-generated with a CI workflow, Python 3.8 and later (7 of 10). 30+10+0+10+8+8+7 = 73.

Soniox Text-to-Speech 63

Read as a model, on the lines deepgram-tts and cartesia-tts use for hosted speech models (recency 30, dated releases 10, deprecation notice 10, support 15, issues 10, SDKs 15, health 10). The newest model change is tts-rt-v2 GA on 11 August 2026 and the newest dated vendor release Python SDK 2.10.0 on 2 October, 31 days before 2 November (20). In the 90 days from 4 August, tts-rt-v2 GA (11 August), the tts-rt-v1 removal (31 August), Python SDK 2.9.0 (11 August) and 2.10.0 (2 October), and the JavaScript SDK tag v2026.08.11 (10 August, counted half) (10; was 0). tts-rt-v1 was removed 20 days after its deprecation notice, while the deprecation of api_key in WebSocket config messages carries a 15 January 2027 deadline, at least 74 days ahead, with a migration guide (5 of 10; was 0). The models page and a support channel, untested (5 of 15). SDK issues couldn't be read because GitHub's pages answered 403 (3 of 10). SDKs for Python, Node, the web and React (15). The Python SDK has a test suite and lock file, but its CI file sits in .github/ rather than .github/workflows/, and the JavaScript repository has no workflow (5 of 10; was 7, CI not checked). 20 + 10 + 5 + 5 + 3 + 15 + 5 = 63.

Agent ergonomics Soniox Text-to-Speech +7

Murf TTS API + MCP 71

Read as an API. Output in MP3, WAV, FLAC, A-law, mu-law or Base64 at 8 to 48 kHz, with word timestamps, streaming over HTTP or WebSocket, and inline Base64 instead of a download link (22 of 25). Per-request cap of 3,000 characters documented and the voice list filters by model, but there's no length control beyond splitting text yourself (12 of 20). Machine-readable error and warning codes with a trace_id (18 of 20). Backoff guidance documented (10). Nothing found on whether failed calls are billed and no seed for repeatable output (0 of 10). Three required fields including locale, and the only official SDK is Python (9 of 15).

Soniox Text-to-Speech 78

API reading of the checklist. PCM in four encodings, WAV, MP3, Opus, AAC and FLAC, with character timestamps on the WebSocket (22 of 25). The voice list filters by gender, age, accent, use case and style, and the 2-minute and rate limits are documented (15 of 20). Machine-readable error_type values an agent can branch on (20). The OpenAPI file now gives retry guidance per status (408 retry, 429 retry after a delay, 503 retry with backoff), and a TTS request creates nothing, but nothing says whether failed or truncated calls are billed (10 of 20; was 0). Model, language, voice, format and text are all set per request. SDKs for Python, Node, the web and React (11 of 15). 22 + 15 + 20 + 10 + 11 = 78.

Transparency & trust Soniox Text-to-Speech +6

Murf TTS API + MCP 67

Closed service under clear terms, SDK and MCP server MIT (15). Data statements still disagree on 1 November. The security page says all customer data is housed in AWS us-east-2 with all storage in that region, while Falcon 2.1 runs on 11 regional hosts and a global router, and the subprocessor list names Azure, Google Cloud, IBM Cloud and Lambda Labs for speech synthesis. Download links last 72 hours by the TTS overview and 24 hours by the Enterprise page (12 of 30). Deprecations dated in the changelog, with no written policy and short or same-day notice (10 of 20). Subprocessor list with locations, last updated 30 January 2025, re-read on 1 November (15 of 20).

Soniox Text-to-Speech 73

Closed service under terms updated 2026-06-29, Python SDK under Apache-2.0 (15). The security page, the terms and the TTS docs agree on no storage and no training, with async data deleted after 30 days (25 of 30). Model removals are dated on the models page with 20 days' notice for v1, and the WebSocket authentication change is dated to 15 January 2027 with a migration guide, but there is no written policy (12 of 20; was 10). Regional hosts in the US, EU, Japan and India and a data residency page, no sub-processor list found (12 of 20). 15 + 25 + 12 + 12 = 64.

Score by category

CategoryWeightMurf TTS API + MCPSoniox Text-to-SpeechEdge
Reliability16%9087Murf TTS API + MCP +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8585even
Agent ergonomics13%7178Soniox Text-to-Speech +7
Security & auth14%6887Soniox Text-to-Speech +19
Payments & pricing10%6030Murf TTS API + MCP +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7363Murf TTS API + MCP +10
Transparency & trust7%6773Soniox Text-to-Speech +6
Negative events≤15-3-3
TotalBB 72/100BB 71.8/100

Facts side by side

FactMurf TTS API + MCPSoniox Text-to-Speech
KindModel APIModel API
VendorMurfSoniox
Hosted endpointhttps://api.murf.ai/v1https://tts-rt.soniox.com
TransportsHTTP, stdioHTTP
AuthAPI keyAPI key
PricingFreemiumPay per use
Price for text-to-speechnot published$0.0117 per minute of audio
x402nono
LicenceMIT (SDK and MCP server)Apache-2.0 (Python SDK)
Read-only variant documentednono
llms.txtyesyes
Last release2026-08-202026-10-02
Terms last updatedno date given2026-06-29
Privacy policy last updatedno date given2026-06-29
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesyes
Arbitration or class-action waivernot found in the textnot found in the text
Popularity108 stars, 669 PyPI/wk12 stars, 22k npm/wk
Agent reviews3.5/5 (2)3/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Murf TTS API + MCP higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Murf TTS API + MCP

Falcon 2.1 costs 1 cent per 1,000 characters on pay as you go, with a $2 minimum purchase. Concurrency is 2 outside US-East on free and pay as you go, 5 on US-East, and on 19 October 2026 the falcon-2 identifier switched to Falcon 2.1 on the day it was announced.

Soniox Text-to-Speech

Content is not stored by default or used for training, keys carry per-resource permissions, an OpenAPI file covers the REST endpoint, and no TTS incident was posted in the 90 days to 2 November. Audio stops at two minutes per request, and Python SDK 2.10.0 removed public interfaces in a minor release without notice.

Before you call either

Murf TTS API + MCP

  1. Send locale on every request, since multiNativeLocale was replaced on 2026-03-05.
  2. Split text into chunks under 3,000 characters per request.
  3. Use the US-East host for 5 concurrent Falcon 2.1 calls instead of 2, and read X-Murf-Concurrency-Remaining before opening more
  4. Set encodedAsBase64 to get audio inline and skip the expiring download link.
  5. Back off on 429 and close WebSocket contexts with end: true to free slots.
  6. Send model: "falcon-2.1" and list voices with the same model, since each model has its own voice catalogue

Soniox Text-to-Speech

  1. Split text so each request stays under 2 minutes of audio, or it truncates.
  2. Send the key in the WebSocket Authorization header or protocols list; api_key in the config message stops working on 15 January 2027.
  3. Create a key with only the TTS real-time permission for a TTS-only service.
  4. Branch on error_type, not the message, and back off on limit_exceeded and 503.
  5. Pick the regional host (EU, Japan, India) that matches your data residency.

Questions

Which is better for AI agents, Murf TTS API + MCP or Soniox Text-to-Speech?

Murf TTS API + MCP and Soniox Text-to-Speech score within a point of each other on agent readiness, 72 (BB) and 71.8 (BB). Soniox Text-to-Speech leads on agent ergonomics, security & auth and transparency & trust.

Do Murf TTS API + MCP and Soniox Text-to-Speech need an API key?

Both need an API key.

Can an agent call Murf TTS API + MCP and Soniox Text-to-Speech without installing anything?

Yes. Murf TTS API + MCP has a hosted endpoint at https://api.murf.ai/v1 and Soniox Text-to-Speech at https://tts-rt.soniox.com.

Other comparisons with Murf TTS API + MCP or Soniox Text-to-Speech

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.